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

    Neuronpedia

    INDEX
    Explanations

    instances of human emotions and existential themes

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

    the definite article "the"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ifikationer
    -0.51
    MockBean
    -0.47
     Violation
    -0.44
    modular
    -0.43
    Violation
    -0.43
     financiero
    -0.41
    JspWriter
    -0.41
    Modular
    -0.41
     Vau
    -0.40
    دانشنامهٔ
    -0.40
    POSITIVE LOGITS
    BeginContext
    0.47
     nakalista
    0.45
    irited
    0.42
    GOTREF
    0.42
    Билгалдахарш
    0.41
    principalTable
    0.41
    WindowConstants
    0.41
     poved
    0.40
    PostInfinity
    0.40
    NullCheck
    0.36
    Act Density 0.004%

    No Known Activations