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

    Neuronpedia

    INDEX
    Explanations

    parentheses and delimiters commonly used in programming syntax

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

    closing code blocks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    aarrggbb
    -0.86
    ftagPool
    -0.81
     للاسماء
    -0.79
    GEBURTSDATUM
    -0.72
     AssemblyTitle
    -0.72
     AssemblyCompany
    -0.69
    IntoConstraints
    -0.69
    TargetException
    -0.67
    sizeCache
    -0.67
    EndProject
    -0.67
    POSITIVE LOGITS
     Landwirtschaft
    0.36
     inmediato
    0.34
     then
    0.34
     realização
    0.33
     descobrir
    0.32
     hopefully
    0.31
     ancianos
    0.31
     Verw
    0.31
    then
    0.30
     prácti
    0.30
    Act Density 0.005%

    No Known Activations