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

    Neuronpedia

    INDEX
    Explanations

    the, comma, and

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ศ
    -0.07
    elim
    -0.07
    .borderWidth
    -0.07
    帅
    -0.07
     Dep
    -0.07
    畚
    -0.07
    eut
    -0.06
    first
    -0.06
    剩下的
    -0.06
    $"
    -0.06
    POSITIVE LOGITS
    进展
    0.07
     seminars
    0.07
    _OPEN
    0.07
        ↵↵↵
    0.06
    ショップ
    0.06
     найти
    0.06
    反转
    0.06
     komb
    0.06
    ">',
    0.06
     xuống
    0.06
    Act Density 0.027%

    No Known Activations