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

    Neuronpedia

    INDEX
    Explanations

    words or phrases indicating a negative condition or state

    oai_token-act-pair · gemini-2.0-flash

    negation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    exitRule
    -0.66
     Efq
    -0.60
    intios
    -0.59
     المعيارى
    -0.59
     Abstr
    -0.59
    UnusedPrivate
    -0.57
    __(/*!
    -0.57
    ^(@)
    -0.56
     LoginComponent
    -0.56
     NSCoder
    -0.54
    POSITIVE LOGITS
     autorytatywna
    0.56
     ex
    0.53
    Pautan
    0.46
    uride
    0.44
     Ex
    0.44
    ńcu
    0.44
     Loomis
    0.42
    thien
    0.42
     amp
    0.42
    Ex
    0.42
    Act Density 1.707%

    No Known Activations