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

    Neuronpedia

    INDEX
    Explanations

    Same (in other languages)

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _LAST
    -0.08
    .getcwd
    -0.07
    _RECORD
    -0.07
     breakdown
    -0.07
    .write
    -0.07
    _RETURN
    -0.07
    _place
    -0.07
    _SELECT
    -0.07
    _work
    -0.07
    _ALLOC
    -0.07
    POSITIVE LOGITS
     одинаков
    0.14
     একই
    0.13
     एउ
    0.13
     группы
    0.13
     동일
    0.12
     grouped
    0.12
     그룹
    0.12
     охшаш
    0.12
    _same
    0.12
     같은
    0.11
    Act Density 0.029%

    No Known Activations