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

    Neuronpedia

    INDEX
    Explanations

    comparative references to alternatives or other entities

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

    distinguishing from others

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    WebpackPlugin
    -0.53
     CSRF
    -0.45
     BAS
    -0.38
    BART
    -0.38
     Parcel
    -0.38
    Бахар
    -0.38
     Physics
    -0.37
    Portail
    -0.37
     Bassett
    -0.37
    hoop
    -0.37
    POSITIVE LOGITS
     invokingState
    0.66
    ftagPool
    0.57
    AndEndTag
    0.56
    parsedMessage
    0.49
     demás
    0.47
     autorytatywna
    0.45
     demais
    0.45
     précédente
    0.45
    verhältnisse
    0.44
     panoramique
    0.44
    Act Density 0.031%

    No Known Activations