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

    Neuronpedia

    INDEX
    Explanations

    specific quantifiable metrics or indicators related to scientific or statistical analysis

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

    before technical or uncommon terms

    np_acts-logits-general · gemini-2.0-flash

    scientific and technical terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     qualcosa
    -0.65
    Hopefully
    -0.64
    Obviously
    -0.61
     hopefully
    -0.61
     obviously
    -0.60
     fameux
    -0.59
     Hopefully
    -0.59
     irgend
    -0.58
     Obviously
    -0.57
     évidemment
    -0.56
    POSITIVE LOGITS
     autorytatywna
    0.96
     AppModule
    0.67
    '".
    0.66
    Havolalar
    0.64
    Autoritní
    0.63
     transférez
    0.63
    rungsseite
    0.62
     kaarangay
    0.60
     CallOverrides
    0.60
    ":
    0.59
    Act Density 1.019%

    No Known Activations