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

    Neuronpedia

    INDEX
    Explanations

    turn

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ада
    -0.07
    ова
    -0.07
    H
    -0.07
    rd
    -0.07
    ше
    -0.07
    ون
    -0.06
     самом
    -0.06
    most
    -0.06
    Ã
    -0.06
    ра
    -0.06
    POSITIVE LOGITS
     신청
    0.08
     vyd
    0.07
    _eng
    0.06
     無
    0.06
    역
    0.06
     She
    0.06
    記
    0.06
     이용
    0.06
    、三
    0.06
    ,eg
    0.06
    Act Density 0.147%

    No Known Activations