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

    Neuronpedia

    INDEX
    Explanations

    Code/math formulas

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     lodge
    -0.07
     شركة
    -0.07
    意味
    -0.07
     encodeURIComponent
    -0.06
    方式
    -0.06
    似乎
    -0.06
     League
    -0.06
    確
    -0.06
    ＜
    -0.06
    очку
    -0.06
    POSITIVE LOGITS
     deltaTime
    0.07
     returnValue
    0.06
    breadcrumbs
    0.06
    �
    0.06
    _MIC
    0.06
    Rot
    0.06
    Æ
    0.06
    [Test
    0.06
     Phillies
    0.06
    iyas
    0.06
    Act Density 0.021%

    No Known Activations