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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions or problems requiring calculations

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

    Letters within math problems

    np_acts-logits-general · gemini-2.0-flash

    closing parenthesis followed by letter

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     (
    -0.77
    (
    -0.53
     ("
    -0.48
      
    -0.46
     –
    -0.45
     correspon
    -0.45
     again
    -0.45
     corresponding
    -0.45
    :
    -0.45
    (`
    -0.43
    POSITIVE LOGITS
     disambiguazione
    0.87
     ujednoznacz
    0.85
     ExecuteAsync
    0.85
    InjectAttribute
    0.83
     initComponents
    0.83
     Meksiku
    0.82
    AndEndTag
    0.81
     שוליים
    0.81
    verwijspagina
    0.80
    yntaxException
    0.79
    Act Density 0.348%

    No Known Activations