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

    Neuronpedia

    INDEX
    Explanations

    numerical values related to quantities or measurements

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

    Tokens after hyphens or numbers

    np_acts-logits-general · gemini-2.0-flash

    numerical divisions or periods

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    TintMode
    -0.80
     estekak
    -0.72
     myſelf
    -0.69
    expandindo
    -0.69
     contextLoads
    -0.68
    Demografie
    -0.66
    PerformLayout
    -0.65
     himſelf
    -0.64
     Theſe
    -0.64
    qrstuvwxyz
    -0.64
    POSITIVE LOGITS
    part
    0.74
     part
    0.70
     prong
    0.59
    prong
    0.53
    person
    0.50
     person
    0.48
     JADX
    0.47
    par
    0.47
    Part
    0.46
    location
    0.44
    Act Density 0.157%

    No Known Activations