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

    Neuronpedia

    INDEX
    Explanations

    boiling water

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    AN
    0.79
    ุ
    0.73
    ل
    0.68
     conlleva
    0.67
     necessario
    0.63
    ان
    0.63
    اي
    0.63
    <0x86>
    0.62
    على
    0.61
     wszyscy
    0.61
    POSITIVE LOGITS
     for
    0.78
    𝟬
    0.68
    ified
    0.66
    ov
    0.65
    叟
    0.62
    )。
    0.60
    ification
    0.59
    ured
    0.58
    ofinstagram
    0.57
     of
    0.56
    Act Density 0.000%

    No Known Activations