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

    Neuronpedia

    INDEX
    Explanations

    math problems

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    TOKEN
    -0.07
    目的
    -0.06
     CCD
    -0.06
    _TER
    -0.06
    _Part
    -0.06
    گانی
    -0.06
    _study
    -0.06
    _OR
    -0.06
     purity
    -0.06
    _texture
    -0.06
    POSITIVE LOGITS
    isodes
    0.07
     مقاله
    0.06
     thẩm
    0.06
    .Mobile
    0.06
     thinking
    0.06
    ATAB
    0.06
     referees
    0.06
     sextreffen
    0.06
     defaultCenter
    0.06
     ios
    0.06
    Act Density 0.003%

    No Known Activations