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

    Neuronpedia

    INDEX
    Explanations

    /

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     crc
    -0.08
     consideration
    -0.07
     readability
    -0.06
     ※
    -0.06
     chemotherapy
    -0.06
    キャンペ
    -0.06
    ynn
    -0.06
    _MY
    -0.06
     comprehension
    -0.06
    巧合
    -0.06
    POSITIVE LOGITS
    체
    0.07
    Transfer
    0.07
    specified
    0.07
     mulheres
    0.07
     workplace
    0.07
     melt
    0.06
     tư
    0.06
    ثير
    0.06
    çı
    0.06
     crédito
    0.06
    Act Density 0.006%

    No Known Activations