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

    Neuronpedia

    INDEX
    Explanations

    ugg

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     devastation
    -0.09
     тұрған
    -0.09
     سرمایہ
    -0.09
     durmuş
    -0.09
     ổ
    -0.08
     stabilité
    -0.08
    勤
    -0.08
     küll
    -0.08
    рали
    -0.08
     pencils
    -0.08
    POSITIVE LOGITS
    _into
    0.08
     weapon
    0.08
     into
    0.08
     illicit
    0.07
     circumvent
    0.07
    Into
    0.07
    weapon
    0.07
    .loads
    0.07
    .weapon
    0.07
     information
    0.07
    Act Density 0.004%

    No Known Activations