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

    Neuronpedia

    INDEX
    Explanations

    references to email communication and its potential enhancements

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

    other

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ########.
    -0.57
     المعيارى
    -0.50
    NameInMap
    -0.49
     Parac
    -0.49
    AnchorStyles
    -0.49
     houſe
    -0.48
    ſelf
    -0.48
     pleaſure
    -0.48
    ftest
    -0.47
    neſs
    -0.46
    POSITIVE LOGITS
    autres
    0.49
    otras
    0.41
     other
    0.39
     інших
    0.38
     inzwischen
    0.37
     otros
    0.37
     mittlerweile
    0.37
     anderen
    0.36
     другие
    0.36
     outros
    0.36
    Act Density 0.121%

    No Known Activations