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

    Neuronpedia

    INDEX
    Explanations

    University

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    评选
    -0.07
    _BT
    -0.07
    /Images
    -0.06
     Alignment
    -0.06
    中期
    -0.06
     please
    -0.06
    配音
    -0.06
    ⯈
    -0.06
    .Auth
    -0.06
    充电
    -0.06
    POSITIVE LOGITS
     Economy
    0.07
    дум
    0.07
    거리
    0.07
     kitabı
    0.07
    ulum
    0.07
    ámara
    0.06
    갱
    0.06
    -bo
    0.06
    עיון
    0.06
    etat
    0.06
    Act Density 0.027%

    No Known Activations