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

    Neuronpedia

    INDEX
    Explanations

    profit target, risk, threats

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     প্রত
    0.46
    dogs
    0.44
     glaciers
    0.43
     suff
    0.42
     locks
    0.42
    Fat
    0.41
    Band
    0.41
    ces
    0.40
     dragons
    0.40
     capacitación
    0.40
    POSITIVE LOGITS
    หรือ
    0.52
    мино
    0.50
    䅐
    0.50
    涀
    0.50
    絴
    0.50
    .,"
    0.49
    ।-
    0.49
    ेंद्र
    0.49
     |.
    0.48
    лимпий
    0.48
    Act Density 0.000%

    No Known Activations