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

    Neuronpedia

    INDEX
    Explanations

    ms

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    但现在
    -0.07
    sets
    -0.07
    scriber
    -0.07
    清算
    -0.07
    DONE
    -0.07
     glyc
    -0.07
    苍白
    -0.07
     capabilities
    -0.07
     phấn
    -0.07
    .SEVERE
    -0.07
    POSITIVE LOGITS
    非遗
    0.07
    مواف
    0.07
     עבוד
    0.07
    .ToLower
    0.07
    .ToUpper
    0.07
     proof
    0.07
    elay
    0.07
    wał
    0.07
    _strike
    0.06
    嘏
    0.06
    Act Density 0.001%

    No Known Activations