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

    Neuronpedia

    INDEX
    Explanations

    Code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    日本
    -0.08
    當您
    -0.07
    趋势
    -0.07
    .getB
    -0.07
     Histogram
    -0.07
     Auditor
    -0.07
    按下
    -0.07
    列车
    -0.07
    כלכלה
    -0.07
    전자
    -0.07
    POSITIVE LOGITS
    껴
    0.07
     disclosures
    0.07
    aine
    0.06
    Recorder
    0.06
    (library
    0.06
     Sharia
    0.06
    WillDisappear
    0.06
    �
    0.06
    🎀
    0.06
    -ste
    0.06
    Act Density 0.004%

    No Known Activations