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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    氏
    -0.07
     Faith
    -0.07
     зат
    -0.07
     رو
    -0.06
    motion
    -0.06
    拔
    -0.06
    study
    -0.06
    ober
    -0.06
    tps
    -0.06
     üçüncü
    -0.06
    POSITIVE LOGITS
    UpDown
    0.07
    .getSize
    0.06
    _Reg
    0.06
     působ
    0.06
     sürec
    0.06
    унок
    0.06
    ).'</
    0.06
    Often
    0.06
    등학교
    0.06
    /pl
    0.05
    Act Density 0.232%

    No Known Activations