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

    Neuronpedia

    INDEX
    Explanations

    conversions, decisions, putting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    tml
    0.48
    &
    0.42
    duk
    0.42
    kuu
    0.41
    animate
    0.40
    がなく
    0.40
    ۶
    0.39
    db
    0.38
    Time
    0.38
     ゲーム
    0.38
    POSITIVE LOGITS
    नल
    0.51
     края
    0.47
    ยาก
    0.47
     openc
    0.46
    屐
    0.45
    ামত
    0.45
     Chassis
    0.44
    ₂+
    0.44
    髋
    0.44
     вас
    0.44
    Act Density 0.002%

    No Known Activations