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

    Neuronpedia

    INDEX
    Explanations

    references and examples in academic or technical writing

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

    providing additional details

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    /*
    -0.46
     LOGGER
    -0.40
    HttpDelete
    -0.40
    يميديا
    -0.37
    ništvo
    -0.37
     CGPoint
    -0.35
     HM
    -0.35
    GetAsync
    -0.35
     IService
    -0.35
    usleep
    -0.35
    POSITIVE LOGITS
     snippetHide
    0.67
     detailed
    0.65
    脚注の使い方
    0.54
     suggestions
    0.54
     additional
    0.53
    ugges
    0.51
     explanations
    0.51
     examples
    0.51
     الحره
    0.51
     details
    0.50
    Act Density 0.078%

    No Known Activations