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

    Neuronpedia

    INDEX
    Explanations

    specific follow-ups

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ب
    1.60
    و
    1.55
     식으로
    1.54
    ために
    1.47
    いて
    1.45
     externalities
    1.42
    ot
    1.41
     doméstica
    1.41
    u
    1.38
    os
    1.38
    POSITIVE LOGITS
    bahan
    1.45
     Meas
    1.41
    Ι
    1.41
    ى
    1.38
    PLACE
    1.38
    ని
    1.35
    ukuran
    1.34
     Objet
    1.34
    Number
    1.30
    MIER
    1.30
    Act Density 0.483%

    No Known Activations