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

    Neuronpedia

    INDEX
    Explanations

    phrases related to programming and software development

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

    default settings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     famous
    -0.47
     internally
    -0.46
     surla
    -0.45
     secretly
    -0.45
    igshid
    -0.44
     unheard
    -0.44
     domestically
    -0.43
     amazingly
    -0.43
    -0.42
     unbelievably
    -0.41
    POSITIVE LOGITS
     мәкал
    0.64
     gyhoeddwyd
    0.52
    Rujuakan
    0.52
    /*
    0.45
    Datuak
    0.44
    Географиясе
    0.44
     poveznice
    0.44
     Мексичка
    0.43
    тьяна
    0.42
    bibfield
    0.42
    Act Density 0.001%

    No Known Activations