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

    Neuronpedia

    INDEX
    Explanations

    rearr

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    '||
    -0.08
    .....
    -0.07
     IllegalStateException
    -0.07
     Byte
    -0.07
    uge
    -0.07
    ..."↵
    -0.07
    稍稍
    -0.07
     Nel
    -0.06
     Monthly
    -0.06
    .tex
    -0.06
    POSITIVE LOGITS
    sanız
    0.07
    מוני
    0.07
    𥔲
    0.07
    �
    0.07
    “There
    0.06
    رحم
    0.06
    grpc
    0.06
    两条
    0.06
    สร
    0.06
    大队
    0.06
    Act Density 0.005%

    No Known Activations