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

    Neuronpedia

    INDEX
    Explanations

    company rankings/growth

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _while
    -0.09
    上的
    -0.07
     있어서
    -0.06
    오는
    -0.06
    lisi
    -0.06
    CreatedBy
    -0.06
    あった
    -0.06
    ;}
    -0.06
    Their
    -0.06
     Між
    -0.06
    POSITIVE LOGITS
    ۲۰۱
    0.07
    ereotype
    0.07
     aggregated
    0.07
     controller
    0.07
     podium
    0.07
    'class
    0.06
    elah
    0.06
     veget
    0.06
     prejud
    0.06
    ्रपत
    0.06
    Act Density 0.021%

    No Known Activations