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

    Neuronpedia

    INDEX
    Explanations

    base

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Thesis
    -0.07
    颞
    -0.07
     Osaka
    -0.07
    Angle
    -0.07
    ても
    -0.06
     baş
    -0.06
     Supplement
    -0.06
    动漫
    -0.06
    格網站
    -0.06
    Wallet
    -0.06
    POSITIVE LOGITS
     الدولية
    0.07
    ixed
    0.07
     produto
    0.07
    +c
    0.07
    _reduction
    0.07
    stitial
    0.07
    #a
    0.07
    적으로
    0.06
     ذ
    0.06
    given
    0.06
    Act Density 0.028%

    No Known Activations