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

    Neuronpedia

    INDEX
    Explanations

    function calls and their parameters in code

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

    use vs method

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ValueStyle
    -0.75
    AddTagHelper
    -0.63
    Portale
    -0.63
    Datuak
    -0.62
     nakalista
    -0.62
    __':
    -0.60
    adaptiveStyles
    -0.59
    expandindo
    -0.59
    aarrggbb
    -0.58
     genti
    -0.56
    POSITIVE LOGITS
     method
    0.47
     used
    0.40
     digunakan
    0.40
     usarlo
    0.39
     rodillas
    0.39
     function
    0.38
     command
    0.37
     kullan
    0.36
    usado
    0.36
    verhalten
    0.36
    Act Density 0.173%

    No Known Activations