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

    Neuronpedia

    INDEX
    Explanations

    lists, code, and instructions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     influence
    0.29
    illae
    0.27
    !),
    0.26
     usually
    0.24
     dị
    0.24
    wark
    0.24
     affect
    0.23
    !=
    0.23
    骈
    0.23
     Acts
    0.23
    POSITIVE LOGITS
     шриф
    0.25
    ↵↵↵↵↵↵↵↵↵↵↵
    0.25
    сны
    0.25
     команда
    0.25
     टन
    0.24
     기타
    0.24
     XNUMX
    0.24
     나머
    0.24
     Ко
    0.24
     konusunda
    0.24
    Act Density 0.239%

    No Known Activations