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

    Neuronpedia

    INDEX
    Explanations

    words related to academic institutions and their associated names

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

    Tokens after a period or underscore

    np_acts-logits-general · gemini-2.0-flash

    Nancy Grace, nauseating

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     للاسماء
    -0.62
    intios
    -0.61
     notice
    -0.61
     notification
    -0.61
    UIControlState
    -0.59
     nomination
    -0.59
     nervous
    -0.58
     normalized
    -0.58
     gynhyrchwyd
    -0.58
     normalize
    -0.58
    POSITIVE LOGITS
     veau
    0.63
    发表于
    0.59
     defaultstate
    0.58
    RectangleBorder
    0.56
     stockings
    0.54
    LookAnd
    0.52
    tiest
    0.51
     Chomsky
    0.50
     []:
    0.50
    ---|---|
    0.49
    Act Density 0.554%

    No Known Activations