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

    Neuronpedia

    INDEX
    Explanations

    smoke

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     smoke
    -1.01
     Smoke
    -0.88
    smoke
    -0.75
    Smoke
    -0.74
     humo
    -0.66
    ses
    -0.64
    cio
    -0.63
    a
    -0.62
    Smoking
    -0.59
     fingerprint
    -0.58
    POSITIVE LOGITS
     समीक्षाएं
    0.70
    DNEY
    0.64
    EDEFAULT
    0.64
     kasarigan
    0.63
     <=",
    0.61
    MLLoader
    0.60
     <>",
    0.57
    télé
    0.56
     intStringLen
    0.56
     Relations
    0.55
    Act Density 0.088%

    No Known Activations