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

    Neuronpedia

    INDEX
    Explanations

    references to data visualizations and mathematical representations

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

    HTML or XML closing tags

    np_acts-logits-general · gemini-2.0-flash

    secondly or footer

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     kaynağından
    -0.53
    ValueStyle
    -0.51
     Parthen
    -0.49
     Andalu
    -0.48
     GenerationType
    -0.48
     Saratoga
    -0.47
     Tash
    -0.45
     confor
    -0.45
     Catawiki
    -0.45
    Incl
    -0.45
    POSITIVE LOGITS
    Secondly
    0.44
    LookAnd
    0.43
    TestingModule
    0.42
     désolés
    0.42
     Secondly
    0.41
    KURZBESCHREIBUNG
    0.40
     secondly
    0.40
    Autoritní
    0.39
    RTLR
    0.37
    <?
    0.37
    Act Density 0.713%

    No Known Activations