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

    Neuronpedia

    INDEX
    Explanations

    Assembly code context

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    的信心
    -0.07
    "--
    -0.07
     COURT
    -0.07
    isz
    -0.07
     pressure
    -0.06
     repercussions
    -0.06
     nec
    -0.06
     cited
    -0.06
    ำ
    -0.06
    .RELATED
    -0.06
    POSITIVE LOGITS
    htable
    0.07
    秦皇
    0.07
    booking
    0.07
    _pts
    0.07
    changing
    0.07
    安全生产
    0.06
     singleton
    0.06
    一期
    0.06
    惑
    0.06
    shapes
    0.06
    Act Density 0.043%

    No Known Activations