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

    Neuronpedia

    INDEX
    Explanations

    instances or forms of blank spaces or placeholders in code

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

    foreign words or code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    aarrggbb
    -0.60
     Wiktionnaire
    -0.60
     TextInputType
    -0.58
     GenerationType
    -0.58
    writeField
    -0.57
    Rujuakan
    -0.56
    Cyfarwyddwr
    -0.55
    messageInfo
    -0.54
    onOptions
    -0.54
    VersionUID
    -0.54
    POSITIVE LOGITS
     gevol
    0.50
     riuscito
    0.50
     democrática
    0.42
     arbejde
    0.41
     zelve
    0.41
     terdapat
    0.40
     mulia
    0.40
     Aussicht
    0.40
     betrokken
    0.40
     ontdek
    0.39
    Act Density 0.010%

    No Known Activations