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

    Neuronpedia

    INDEX
    Explanations

    what can I do for you

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    v
    1.71
    d
    1.66
    l
    1.52
    n
    1.49
    de
    1.33
    ll
    1.30
    p
    1.27
    t
    1.26
    ma
    1.20
    g
    1.16
    POSITIVE LOGITS
    ের
    0.94
     refunds
    0.93
     defeats
    0.92
     invasion
    0.89
     copyrights
    0.89
     andDevice
    0.89
    ات
    0.88
    ாம்
    0.88
    -
    0.87
     audacity
    0.85
    Act Density 0.000%

    No Known Activations