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

    Neuronpedia

    INDEX
    Explanations

    elements related to evaluation or validation processes

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

    Text occurring within parentheses or brackets

    np_acts-logits-general · gemini-2.0-flash

    lists of code, options, or items

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     véritables
    -0.50
     véritable
    -0.46
     dumne
    -0.45
     désigner
    -0.45
     verdaderos
    -0.44
     című
    -0.43
     malheure
    -0.42
     coloro
    -0.42
     hudeb
    -0.42
     menghabiskan
    -0.42
    POSITIVE LOGITS
    :✨
    1.01
    ValueStyle
    0.99
    AddTagHelper
    0.96
    DoubleQuotes
    0.96
     Мексичка
    0.94
    AccessorTable
    0.93
     tartalomajánló
    0.92
     kasarigan
    0.91
     AssemblyTitle
    0.91
     defaultstate
    0.90
    Act Density 0.857%

    No Known Activations