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

    Neuronpedia

    INDEX
    Explanations

    purpose or consequence

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    al
    0.62
     Δη
    0.47
    four
    0.46
    Policy
    0.45
    h
    0.43
    Authors
    0.42
    fourth
    0.42
    ate
    0.42
    iev
    0.42
    ofa
    0.41
    POSITIVE LOGITS
     outpost
    0.46
    メール
    0.45
     окра
    0.43
     ক্লাব
    0.43
     attaché
    0.42
    JECTION
    0.42
    蕪
    0.42
     shrines
    0.41
     picnics
    0.41
     gathering
    0.41
    Act Density 0.004%

    No Known Activations