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

    Neuronpedia

    INDEX
    Explanations

    capes and powers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     calyce
    0.43
     CMV
    0.42
     indicative
    0.41
     glycos
    0.41
     japonesa
    0.41
    ويض
    0.41
     सेक
    0.40
     naal
    0.40
    сного
    0.39
    汨
    0.39
    POSITIVE LOGITS
     Ruth
    0.95
    Ruth
    0.83
     ру
    0.73
     Ру
    0.62
     Rupert
    0.61
    RU
    0.59
     রু
    0.57
     Lady
    0.56
     Mrs
    0.56
     ru
    0.55
    Act Density 0.000%

    No Known Activations