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

    Neuronpedia

    INDEX
    Explanations

    items related to recommendations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     emitted
    0.52
    粳
    0.50
     Reading
    0.49
     Readable
    0.48
    Reading
    0.48
    Qin
    0.48
    Список
    0.46
     различные
    0.46
    abilidades
    0.46
    шымта
    0.46
    POSITIVE LOGITS
     따라
    0.52
     기본
    0.52
     타
    0.51
     검색
    0.50
     솔
    0.49
    들
    0.49
    다
    0.48
     프
    0.48
     가
    0.48
     소
    0.47
    Act Density 0.030%

    No Known Activations