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

    Neuronpedia

    INDEX
    Explanations

    flexibility

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     довольно
    0.78
     bonnes
    0.74
     ônibus
    0.70
     puertos
    0.69
     ম
    0.68
     dobr
    0.68
     caliente
    0.68
     Durante
    0.68
     sassy
    0.67
     досить
    0.66
    POSITIVE LOGITS
    ا
    1.16
    ing
    1.06
    us
    0.98
    a
    0.98
    he
    0.95
     Flexibility
    0.93
     flexibility
    0.91
    та
    0.85
    ie
    0.85
    ای
    0.82
    Act Density 0.009%

    No Known Activations