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

    Neuronpedia

    INDEX
    Explanations

    non-English words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    !↵↵
    -0.06
     dtype
    -0.06
    /Add
    -0.06
    ść
    -0.06
    Unt
    -0.06
    _store
    -0.06
     MON
    -0.06
     สำหร
    -0.06
     Attempt
    -0.06
    ovaný
    -0.06
    POSITIVE LOGITS
     중앙
    0.08
    .setResult
    0.07
    .FETCH
    0.07
    and
    0.06
    structures
    0.06
     cena
    0.06
    IconButton
    0.06
     Cena
    0.06
    usiness
    0.06
    厅
    0.06
    Act Density 0.035%

    No Known Activations