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

    Neuronpedia

    INDEX
    Explanations

    new beginnings and growth

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     centrale
    0.43
    済
    0.39
     chở
    0.38
     youre
    0.38
     Enroll
    0.38
     Sends
    0.38
     définitive
    0.37
     ہوگئی
    0.37
     عادة
    0.37
    𝕟
    0.37
    POSITIVE LOGITS
     numeros
    0.48
    smooth
    0.47
    шу
    0.44
     cohorts
    0.43
    numero
    0.42
    em
    0.41
    岕
    0.41
     berm
    0.41
     malas
    0.40
    ഇ
    0.40
    Act Density 0.001%

    No Known Activations