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

    Neuronpedia

    INDEX
    Explanations

    providing solutions or help

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     those
    0.44
     appr
    0.43
    らの
    0.42
    _{
    0.41
     pretty
    0.41
    rend
    0.41
     より
    0.41
     opaque
    0.41
     contemporaries
    0.41
    }
    0.41
    POSITIVE LOGITS
     soluções
    0.46
    летний
    0.45
    िल्स
    0.44
    Tickets
    0.42
     Vitória
    0.42
     ٹرسٹ
    0.42
    맙
    0.42
     apostila
    0.41
    फलता
    0.41
     прибыль
    0.41
    Act Density 0.000%

    No Known Activations