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

    Neuronpedia

    INDEX
    Explanations

    late game threat

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     मोटी
    0.52
     avoiding
    0.51
     добавить
    0.51
     கோட்ப
    0.49
    рных
    0.48
     BGPS
    0.46
     পৌঁ
    0.46
     assuring
    0.46
    ার
    0.46
     gins
    0.46
    POSITIVE LOGITS
    !
    0.48
    ình
    0.46
    ?
    0.43
    '
    0.43
    Silence
    0.42
    ཇ
    0.42
    ڑھ
    0.42
     Rite
    0.42
     lament
    0.41
    ɾ
    0.41
    Act Density 0.000%

    No Known Activations