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

    Neuronpedia

    INDEX
    Explanations

    Hamlet

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    훕
    -0.07
    翳
    -0.07
     cen
    -0.07
    parcel
    -0.07
     ofApp
    -0.06
    styl
    -0.06
    aur
    -0.06
    IllegalAccessException
    -0.06
    egas
    -0.06
    冏
    -0.06
    POSITIVE LOGITS
    [U
    0.08
    的距离
    0.07
     jak
    0.07
     distorted
    0.07
    \\\\
    0.07
    /bin
    0.07
    把
    0.07
    DNA
    0.07
    대로
    0.06
     distilled
    0.06
    Act Density 0.003%

    No Known Activations