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

    Neuronpedia

    INDEX
    Explanations

    mathematics

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     لدي
    -0.07
    培训
    -0.07
     spherical
    -0.07
     refrigerator
    -0.07
     ﻣ
    -0.07
     있습니다
    -0.07
     trapping
    -0.07
    .this
    -0.06
    اوي
    -0.06
     기타
    -0.06
    POSITIVE LOGITS
    bler
    0.06
    _RESOURCES
    0.06
     grayscale
    0.06
    들을
    0.06
     코드
    0.06
    REV
    0.06
    �
    0.06
     ně
    0.06
    мент
    0.05
    edics
    0.05
    Act Density 0.020%

    No Known Activations