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

    Neuronpedia

    INDEX
    Explanations

    table

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (px
    -0.07
     바랍니다
    -0.07
    GameObjectWithTag
    -0.07
     فهو
    -0.07
    (tm
    -0.07
    .fe
    -0.07
    [np
    -0.07
    pd
    -0.07
    村党支部
    -0.07
     freeing
    -0.07
    POSITIVE LOGITS
    转折
    0.07
    出口
    0.07
     Norton
    0.07
    ↛
    0.07
     specialist
    0.06
    知识点
    0.06
    ᨬ
    0.06
     Nap
    0.06
    Assets
    0.06
    -sh
    0.06
    Act Density 0.010%

    No Known Activations