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

    Neuronpedia

    INDEX
    Explanations

    expressions of excitement or admiration

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

    aw, awes, awash, awakes, awning

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ReusableCell
    -0.60
     endblock
    -0.57
     NSCoder
    -0.57
    itoneal
    -0.54
    ementara
    -0.54
     Petru
    -0.53
     referenties
    -0.53
    pidou
    -0.53
    exitRule
    -0.52
    ciaż
    -0.52
    POSITIVE LOGITS
     Aw
    1.83
    Aw
    1.65
     aw
    1.59
     AW
    1.49
    AW
    1.27
    aw
    1.11
     Aws
    0.80
     Av
    0.78
     awn
    0.77
     awning
    0.75
    Act Density 0.006%

    No Known Activations