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

    Neuronpedia

    INDEX
    Explanations

    instances of personal physical descriptions and attributes

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

    possessive pronoun followed by noun

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ArgumentParser
    -0.45
    FieldNumber
    -0.39
     immédi
    -0.39
     indépendante
    -0.36
     vectorielle
    -0.36
     féd
    -0.35
     Например
    -0.34
     gioielli
    -0.34
     farma
    -0.34
     Pemer
    -0.34
    POSITIVE LOGITS
     AssemblyCulture
    0.63
     estekak
    0.57
     autorytatywna
    0.52
     OMITBAD
    0.48
     HasFactory
    0.46
     äls
    0.46
     defaultstate
    0.46
     kaynağından
    0.46
    tahui
    0.45
    Chham
    0.45
    Act Density 0.043%

    No Known Activations