Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    references to academic or scientific contexts, particularly relating to research in the social sciences or evolutionary studies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Code related to fragments or empty sets

    np_acts-logits-general · gemini-2.0-flash

    Fragment, emptyset, %

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     MotionEvent
    -0.46
    platin
    -0.44
    HtmlAttribute
    -0.44
    ArrowToggle
    -0.43
     boca
    -0.43
     Pou
    -0.43
    istoitu
    -0.43
    ClientSize
    -0.42
    maus
    -0.42
    cheon
    -0.41
    POSITIVE LOGITS
    Fragment
    1.20
     Fragment
    1.19
     fragment
    1.13
    fragment
    1.12
     fragments
    1.00
     frag
    1.00
     Fragments
    0.98
    FRAGMENT
    0.95
    fragments
    0.94
     FRAG
    0.92
    Act Density 0.076%

    No Known Activations