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

    Neuronpedia

    INDEX
    Explanations

    Quotation marks

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     preaching
    -0.07
     tools
    -0.07
    .Encode
    -0.07
    Acts
    -0.07
    经营理念
    -0.07
    鸩
    -0.07
    螣
    -0.07
     دي
    -0.07
     عبد
    -0.07
     destroy
    -0.07
    POSITIVE LOGITS
    ﺳ
    0.07
     FRAME
    0.07
    /pm
    0.07
     FAMILY
    0.07
    Row
    0.07
    SUMER
    0.07
    HOW
    0.06
    提名
    0.06
    is
    0.06
    GetSize
    0.06
    Act Density 0.003%

    No Known Activations