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

    Neuronpedia

    INDEX
    Explanations

    made, based, calculated, relied

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     SwitchCompat
    0.57
     Sánchez
    0.49
    وم
    0.48
    리가
    0.46
     Stylish
    0.45
     unworthy
    0.45
    ็อก
    0.45
     الشخص
    0.45
    ोदय
    0.45
     guérir
    0.45
    POSITIVE LOGITS
    ’
    0.62
     on
    0.57
    -
    0.55
    producing
    0.54
    time
    0.52
    ite
    0.50
     ph
    0.47
     a
    0.47
     ø
    0.46
    Ų
    0.45
    Act Density 0.001%

    No Known Activations