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

    Neuronpedia

    INDEX
    Explanations

    read write

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     싱
    -0.07
    BASEPATH
    -0.06
    苦
    -0.06
    紹介
    -0.06
     BMI
    -0.06
     covariance
    -0.06
    ۀ
    -0.06
    іття
    -0.06
     кури
    -0.06
     její
    -0.06
    POSITIVE LOGITS
     tường
    0.06
    .original
    0.06
    -purple
    0.06
     Green
    0.06
    ropol
    0.06
    شت
    0.06
     freel
    0.06
    bud
    0.06
    _attack
    0.06
    Ont
    0.06
    Act Density 0.008%

    No Known Activations