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

    Neuronpedia

    INDEX
    Explanations

    Apache license headers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Img
    -0.07
     surgeries
    -0.07
    ाऊ
    -0.06
     Legend
    -0.06
     Иванов
    -0.06
    endra
    -0.06
    (info
    -0.06
    npm
    -0.06
     Rape
    -0.06
    "For
    -0.06
    POSITIVE LOGITS
    ==↵
    0.07
    ώνα
    0.07
     proceed
    0.06
     +=↵
    0.06
     leth
    0.06
    嘴
    0.06
     Rocket
    0.06
    _transfer
    0.06
     militant
    0.06
    ，本
    0.06
    Act Density 0.001%

    No Known Activations