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

    Neuronpedia

    INDEX
    Explanations

    tub and bathtub contexts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Ў
    0.65
    ueve
    0.62
    кові
    0.61
    ľad
    0.60
     rebellious
    0.60
     ერთ
    0.59
    CIES
    0.59
    Ή
    0.58
    ハ
    0.58
    カテゴリー
    0.57
    POSITIVE LOGITS
    ana
    0.83
    v
    0.79
    ت
    0.69
    ot
    0.68
    ani
    0.68
    но
    0.66
    ew
    0.65
    h
    0.64
    การ
    0.63
    oe
    0.62
    Act Density 0.000%

    No Known Activations