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

    Neuronpedia

    INDEX
    Explanations

    journal titles and references in academic writing

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

    References (likely scientific publications)

    np_acts-logits-general · gemini-2.0-flash

    journal names and citations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    |}{$
    -0.84
     BoxFit
    -0.79
     ReSharper
    -0.78
     ModelExpression
    -0.71
     متعلقه
    -0.70
    resave
    -0.69
     AppColors
    -0.69
     fubject
    -0.69
    antry
    -0.67
     Numerade
    -0.65
    POSITIVE LOGITS
    שר
    0.49
     dată
    0.48
     partenza
    0.46
    RegistryLite
    0.46
     lâng
    0.45
     économiques
    0.45
    تل
    0.44
    ten
    0.43
     acolo
    0.43
    temming
    0.42
    Act Density 0.153%

    No Known Activations