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

    Neuronpedia

    INDEX
    Explanations

    code context

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ScopeManager
    -0.51
     étab
    -0.50
    TabStop
    -0.48
    Cordialement
    -0.47
    bildet
    -0.46
     femininas
    -0.46
     getNome
    -0.45
     useEffect
    -0.45
     NKC
    -0.43
     تانيه
    -0.43
    POSITIVE LOGITS
    ьаж
    0.63
    TacToe
    0.52
    Билгалдахарш
    0.52
     '/':
    0.51
     lenker
    0.51
    doctype
    0.51
     שוליים
    0.50
    Kaynakça
    0.50
    Viited
    0.49
    caf
    0.49
    Act Density 0.003%

    No Known Activations