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

    Neuronpedia

    INDEX
    Explanations

    the term related to statements or commands of denial

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

    lists of items

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    +#+#
    -0.65
    Diweddarwch
    -0.58
    IntoConstraints
    -0.56
    bootstrapcdn
    -0.55
    IsContent
    -0.55
    ReusableCell
    -0.53
     himo
    -0.49
    évaluateur
    -0.49
    RTLI
    -0.48
    ValueStyle
    -0.47
    POSITIVE LOGITS
     demasi
    0.42
     dizaines
    0.41
     dozens
    0.41
    redund
    0.41
     redundancy
    0.41
     Abund
    0.39
     flesta
    0.38
    Ouv
    0.38
     Redund
    0.37
    BeginContext
    0.37
    Act Density 0.056%

    No Known Activations