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

    Neuronpedia

    INDEX
    Explanations

    physical descriptions and actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ѕ
    0.45
    xor
    0.40
    Кар
    0.40
     smashing
    0.40
     Ici
    0.38
     好
    0.37
     pigeons
    0.37
    siniz
    0.37
     haunting
    0.36
     Snacks
    0.36
    POSITIVE LOGITS
    ع
    0.49
    로
    0.48
    setWidth
    0.40
    ب
    0.39
    د
    0.38
    то
    0.37
    પ
    0.35
    все
    0.35
    مع
    0.35
    ோ
    0.34
    Act Density 0.091%

    No Known Activations