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

    Neuronpedia

    INDEX
    Explanations

    code-related terms indicating equivalence or consistency

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    code comparison logic

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    windowFixed
    -0.59
     Signalez
    -0.47
     незавершена
    -0.44
     հղումներ
    -0.44
     estekak
    -0.42
     eléct
    -0.42
     LEYENDO
    -0.41
    ImageContext
    -0.41
    ècie
    -0.41
     мәкал
    -0.40
    POSITIVE LOGITS
    {}
    1.01
     {}
    0.80
    ArgsConstructor
    0.53
    {}\
    0.52
     "{}
    0.51
     {}
    0.50
    {}
    0.50
     '{}
    0.48
    ={}
    0.48
    autor
    0.47
    Act Density 0.002%

    No Known Activations