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

    Neuronpedia

    INDEX
    Explanations

    4 8 helpline

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    0.72
     ž
    0.70
    .
    0.68
     mie
    0.68
    decine
    0.68
    的结果
    0.68
     Memory
    0.66
    ursing
    0.66
     pia
    0.65
    :
    0.65
    POSITIVE LOGITS
    ccbp
    0.83
     уйнагыз
    0.83
    tLogRow
    0.80
    <unused1980>
    0.80
    樑
    0.80
     productColor
    0.79
    দুর
    0.79
    傈
    0.79
    Proyecto
    0.79
    BASELINE
    0.79
    Act Density 0.030%

    No Known Activations