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

    Neuronpedia

    INDEX
    Explanations

    references to historical or literary figures and works

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

    placenames and geographical regions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ConstraintMaker
    -0.84
     CreateTagHelper
    -0.80
    MLLoader
    -0.70
    zzleHttp
    -0.69
    AccessorTable
    -0.69
    Personendaten
    -0.68
     للاسماء
    -0.68
     للمعارف
    -0.67
     Roskov
    -0.65
     nahilalakip
    -0.65
    POSITIVE LOGITS
     publicação
    0.37
     Victorian
    0.35
     gedaan
    0.34
     updatedAt
    0.33
     cập
    0.32
     originais
    0.32
     Methoden
    0.32
     nød
    0.32
     Kindern
    0.32
     Fili
    0.31
    Act Density 0.064%

    No Known Activations