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

    Neuronpedia

    INDEX
    Explanations

    acceptable and contained

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    да
    0.80
    beschreibung
    0.80
    지로
    0.79
     aște
    0.77
    elize
    0.74
    t
    0.74
    um
    0.73
    estable
    0.72
    us
    0.72
     Уен
    0.72
    POSITIVE LOGITS
     psychiatric
    0.78
     ilgili
    0.77
     bazı
    0.71
     maternity
    0.68
    芎
    0.67
     ağı
    0.66
    たり
    0.66
    许多
    0.65
    除此之外
    0.65
    诒
    0.65
    Act Density 0.001%

    No Known Activations