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

    Neuronpedia

    INDEX
    Explanations

    that

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Tic
    -0.07
    .snp
    -0.06
    705
    -0.06
    .mod
    -0.06
    129
    -0.06
     qi
    -0.06
     rehe
    -0.06
     listens
    -0.06
    CG
    -0.05
     �
    -0.05
    POSITIVE LOGITS
     رج
    0.07
    adic
    0.07
    California
    0.07
     Caucasian
    0.06
    mue
    0.06
     strokeLine
    0.06
     máte
    0.06
    홍
    0.06
    human
    0.06
    나
    0.06
    Act Density 0.052%

    No Known Activations