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

    Neuronpedia

    INDEX
    Explanations

    del nombre

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    culpa
    0.43
    CMR
    0.39
    wagen
    0.39
    SWITCH
    0.39
    χι
    0.39
    oló
    0.38
    गाय
    0.38
     توان
    0.38
    uala
    0.37
    olver
    0.37
    POSITIVE LOGITS
     Orwell
    0.41
     khuyến
    0.38
     partake
    0.37
     Som
    0.36
     handheld
    0.35
    げて
    0.34
    न्वयन
    0.34
     Lucas
    0.34
     inspirations
    0.34
    ᄑ
    0.34
    Act Density 0.000%

    No Known Activations