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

    Neuronpedia

    INDEX
    Explanations

    structured code elements and their attributes

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

    everyday spanish words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Paglinawan
    -0.59
    AutoScaleMode
    -0.59
     otomatig
    -0.56
    AndEndTag
    -0.51
    GEBURTSDATUM
    -0.48
     Roskov
    -0.47
    تقاوى
    -0.45
     estekak
    -0.45
     nakalista
    -0.44
     Мексичка
    -0.44
    POSITIVE LOGITS
     esponja
    0.49
     toallas
    0.46
     صوتيه
    0.46
     toalla
    0.46
     calcetines
    0.43
     gimnas
    0.43
     helados
    0.40
    verwijspagina
    0.40
     arcilla
    0.40
     vétérina
    0.40
    Act Density 0.034%

    No Known Activations