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

    Neuronpedia

    INDEX
    Explanations

    CISSP Practitioner exam

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ના
    0.77
    鈮
    0.75
    ες
    0.73
    S
    0.72
    N
    0.71
    さ
    0.71
    카
    0.70
    萠
    0.70
    Fach
    0.69
    Neill
    0.68
    POSITIVE LOGITS
     in
    0.97
    r
    0.82
     armed
    0.79
     amount
    0.76
    0
    0.74
     string
    0.71
     oog
    0.70
     number
    0.69
     altro
    0.69
     altre
    0.68
    Act Density 0.002%

    No Known Activations