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

    Neuronpedia

    INDEX
    Explanations

    Mary and Jesus

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    查
    -0.06
     :]↵
    -0.06
    ρκε
    -0.06
    _\
    -0.06
    绩
    -0.06
    (CL
    -0.06
     indign
    -0.06
    สำหร
    -0.06
    -exc
    -0.06
    特別
    -0.06
    POSITIVE LOGITS
     hunger
    0.07
    一点
    0.06
     зави
    0.06
     europ
    0.06
     postupně
    0.06
     RATE
    0.06
    ヽ
    0.06
    арод
    0.06
    winner
    0.06
    igy
    0.06
    Act Density 0.005%

    No Known Activations