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

    Neuronpedia

    INDEX
    Explanations

    z

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -hours
    -0.07
    445
    -0.06
     Lagos
    -0.06
     hemisphere
    -0.06
    661
    -0.06
     trails
    -0.06
    utut
    -0.06
    孤
    -0.06
    rug
    -0.06
     "+
    -0.06
    POSITIVE LOGITS
    (sz
    0.08
     Dick
    0.07
    sembling
    0.07
    UDGE
    0.07
     evaluated
    0.07
    asz
    0.06
    _DRV
    0.06
    .engine
    0.06
     انگلیسی
    0.06
    ски
    0.06
    Act Density 0.030%

    No Known Activations