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

    Neuronpedia

    INDEX
    Explanations

    machine learning models

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     are
    0.39
    mi
    0.34
    to
    0.33
     is
    0.33
    0.32
     to
    0.31
    ۔
    0.31
    methyl
    0.30
    sp
    0.30
    ml
    0.30
    POSITIVE LOGITS
    ل
    0.47
     for
    0.43
     Modelle
    0.42
    ر
    0.41
    ور
    0.40
    For
    0.39
    et
    0.35
    혔
    0.35
    埒
    0.35
    춰
    0.34
    Act Density 0.340%

    No Known Activations