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

    Neuronpedia

    INDEX
    Explanations

    HTML or coding syntax elements and structures

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

    node above

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    jspx
    -0.47
    şört
    -0.47
    delwed
    -0.47
    めんなさい
    -0.44
    GTCX
    -0.44
    jmniej
    -0.42
    lusconi
    -0.41
    enumi
    -0.41
     />);
    -0.40
    ỡng
    -0.39
    POSITIVE LOGITS
    iyle
    0.45
    Manbalar
    0.45
     quedará
    0.43
     comunicarse
    0.40
     autorytatywna
    0.40
     tacón
    0.39
    pushFollow
    0.39
     gawas
    0.39
    Descripció
    0.38
    Lyric
    0.38
    Act Density 0.012%

    No Known Activations