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

    Neuronpedia

    INDEX
    Explanations

    roles, titles, policies

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     transacción
    0.64
     campo
    0.55
    ionar
    0.54
     comercio
    0.54
     DEALINGS
    0.52
     oeste
    0.52
     piensa
    0.52
     continua
    0.51
     comerci
    0.51
     consistente
    0.51
    POSITIVE LOGITS
    Gar
    0.48
    Level
    0.47
    struktur
    0.47
    od
    0.45
    صب
    0.45
    Hoy
    0.44
    t
    0.44
    قص
    0.44
    Number
    0.44
    of
    0.43
    Act Density 0.000%

    No Known Activations