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

    Neuronpedia

    INDEX
    Explanations

    coming

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    евого
    -0.07
    cling
    -0.06
    hung
    -0.06
    итив
    -0.06
    ++;↵↵
    -0.06
     обо
    -0.06
    琴
    -0.06
     Пов
    -0.06
    .Pool
    -0.06
     atr
    -0.06
    POSITIVE LOGITS
     meine
    0.07
     suppressing
    0.07
    ait
    0.07
     eliminating
    0.06
    _blue
    0.06
     kidding
    0.06
    ọn
    0.06
     grande
    0.06
     Jer
    0.06
    催
    0.06
    Act Density 0.015%

    No Known Activations