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

    Neuronpedia

    INDEX
    Explanations

    rite

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    usting
    -0.07
     deste
    -0.07
    苔
    -0.07
    氯
    -0.07
    洄
    -0.07
    접
    -0.07
    >c
    -0.06
    .BUTTON
    -0.06
    峭
    -0.06
    Ἷ
    -0.06
    POSITIVE LOGITS
     FileName
    0.08
    _retry
    0.08
    .fail
    0.07
     supervised
    0.07
    的数据
    0.07
     Overwatch
    0.07
    _checkpoint
    0.07
     apologized
    0.07
     stable
    0.06
    _statement
    0.06
    Act Density 0.001%

    No Known Activations