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

    Neuronpedia

    INDEX
    Explanations

    dancing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ;
    0.53
    الس
    0.52
    }
    0.50
    cation
    0.50
    of
    0.49
    ofed
    0.48
     at
    0.47
    壮
    0.47
    Coat
    0.47
    الج
    0.47
    POSITIVE LOGITS
    ো
    0.75
    ა
    0.70
    ки
    0.68
     dancing
    0.63
    ת
    0.63
    ться
    0.62
     Texto
    0.61
    ු
    0.61
    ла
    0.60
    ление
    0.60
    Act Density 0.001%

    No Known Activations