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

    Neuronpedia

    INDEX
    Explanations

    code symbols

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     hurting
    -0.07
    quad
    -0.07
     retrospect
    -0.06
     Aid
    -0.06
    <strong
    -0.06
    Gay
    -0.06
     daß
    -0.06
    sthrough
    -0.06
    عام
    -0.06
    Thông
    -0.06
    POSITIVE LOGITS
    =df
    0.07
    astreet
    0.07
     Perf
    0.06
    erglass
    0.06
     đậu
    0.06
     тис
    0.06
     reinforced
    0.06
    ="#
    0.06
     perme
    0.06
     &_
    0.06
    Act Density 0.010%

    No Known Activations