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

    Neuronpedia

    INDEX
    Explanations

    .

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     WWE
    -0.07
    acho
    -0.07
     재
    -0.06
    (:,
    -0.06
    _HIT
    -0.06
    /pass
    -0.06
    ，她
    -0.06
     名無しさん
    -0.06
     시험
    -0.06
    :last
    -0.06
    POSITIVE LOGITS
     bankers
    0.07
    ForegroundColor
    0.07
    Annotation
    0.06
     discussion
    0.06
    ubic
    0.06
    .flag
    0.06
    ру
    0.06
    67
    0.06
     unten
    0.06
    mins
    0.06
    Act Density 0.000%

    No Known Activations