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

    Neuronpedia

    INDEX
    Explanations

    days or durations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     molte
    0.96
     numerose
    0.91
     politica
    0.88
     grabando
    0.88
     noto
    0.86
     CCc
    0.84
     esempi
    0.83
     habido
    0.83
    бера
    0.82
    िता
    0.81
    POSITIVE LOGITS
    sh
    0.82
    ত্বের
    0.80
    个
    0.80
    jun
    0.79
    kan
    0.77
    '
    0.75
    .
    0.75
    ?
    0.75
    Ag
    0.73
    D
    0.73
    Act Density 0.000%

    No Known Activations