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

    Neuronpedia

    INDEX
    Explanations

    bits needed or ordering

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    I
    0.85
    wa
    0.74
    ac
    0.73
    :
    0.73
    ade
    0.71
    inz
    0.70
    ant
    0.70
    atm
    0.70
    $
    0.70
    all
    0.69
    POSITIVE LOGITS
     bits
    0.83
     imóvel
    0.79
     imágenes
    0.76
     espírito
    0.73
     él
    0.73
     electrón
    0.73
    nın
    0.72
    )。
    0.71
     biología
    0.70
     étages
    0.70
    Act Density 0.016%

    No Known Activations