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

    Neuronpedia

    INDEX
    Explanations

    him

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ictions
    -0.09
    reports
    -0.07
    ospels
    -0.07
    เจอ
    -0.07
    UNITY
    -0.07
     Jenner
    -0.07
    ived
    -0.07
    inya
    -0.07
     tersebut
    -0.07
    坐标
    -0.07
    POSITIVE LOGITS
    Commit
    0.07
     Box
    0.07
    整车
    0.07
     Malk
    0.07
     impair
    0.06
    _UN
    0.06
     מח
    0.06
    reflect
    0.06
    分
    0.06
     clinical
    0.06
    Act Density 0.112%

    No Known Activations