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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate excitement or a mess

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

    all and up

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Италијани
    -0.50
     Italijanski
    -0.48
     protoimpl
    -0.47
    addCriterion
    -0.46
     surla
    -0.42
    帖最后由
    -0.40
    Produktion
    -0.38
     crowds
    -0.37
    CLAIMER
    -0.36
     kasarigan
    -0.36
    POSITIVE LOGITS
    一身
    0.48
    literals
    0.46
     RVA
    0.45
    出版年
    0.44
    JsonKey
    0.42
    useNewUrlParser
    0.42
    hols
    0.42
    ordion
    0.41
    nibal
    0.41
    angliski
    0.41
    Act Density 0.024%

    No Known Activations