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

    Neuronpedia

    INDEX
    Explanations

    references to different types or categories

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

    type of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     charité
    -0.52
    */].
    -0.52
     nôtre
    -0.51
    chieht
    -0.50
    ddots
    -0.48
     vôtre
    -0.47
    bootstrapcdn
    -0.46
    CrossRef
    -0.44
     antaranya
    -0.43
     leçon
    -0.43
    POSITIVE LOGITS
    Примі
    0.45
     ip
    0.42
     thiệu
    0.41
    AnchorTagHelper
    0.41
    SizeMode
    0.41
    oa̍t
    0.40
     Stabili
    0.39
     cdi
    0.38
     jit
    0.38
     sentence
    0.38
    Act Density 0.206%

    No Known Activations