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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating types or categories

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

    a type of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     dentaire
    -0.34
     mourut
    -0.31
    arriver
    -0.30
     domestiques
    -0.29
    izarse
    -0.29
    -¿
    -0.29
     these
    -0.29
     sanitarias
    -0.28
    这点
    -0.28
    paravant
    -0.27
    POSITIVE LOGITS
    rungsseite
    0.76
    一種
    0.68
    ContentAlignment
    0.68
    WriteTagHelper
    0.66
    sizeCache
    0.65
    styleable
    0.64
    quasi
    0.63
    tagHelperRunner
    0.63
    saraba
    0.62
     semacam
    0.61
    Act Density 0.018%

    No Known Activations