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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ๅ
    -0.08
    _cost
    -0.07
     ngược
    -0.07
    جامع
    -0.06
    𝘏
    -0.06
     advocates
    -0.06
     aldığı
    -0.06
    ܟ
    -0.06
    צמח
    -0.06
    wę
    -0.06
    POSITIVE LOGITS
     FI
    0.07
     rogue
    0.07
    ston
    0.07
    岛上
    0.07
    )test
    0.07
     Kang
    0.07
    职工
    0.07
    مو
    0.07
     terrorists
    0.07
    /team
    0.06
    Act Density 0.005%

    No Known Activations