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

    Neuronpedia

    INDEX
    Explanations

    references to mathematical expressions or equations

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

    Text within brackets and numbers

    np_acts-logits-general · gemini-2.0-flash

    citation numbers in brackets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     anything
    -0.59
    tanleria
    -0.53
     Anything
    -0.51
     createSprite
    -0.49
     dAtA
    -0.49
    anything
    -0.49
     indietro
    -0.47
     Rave
    -0.45
     Lect
    -0.44
    RUnlock
    -0.43
    POSITIVE LOGITS
    TagMode
    0.59
    berdayakan
    0.58
    henswürdigkeiten
    0.56
    исленность
    0.52
    rogels
    0.50
    __':
    0.50
     غم
    0.50
    Aiheesta
    0.49
    Portale
    0.49
    Identyfik
    0.49
    Act Density 0.234%

    No Known Activations