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

    Neuronpedia

    INDEX
    Explanations

    negations and phrases expressing inability or prohibition

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

    "Can't" followed by a verb

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     familiale
    -0.59
     saliendo
    -0.55
    WireFormatLite
    -0.55
    sums
    -0.52
     Barna
    -0.52
     Refer
    -0.52
    érias
    -0.51
     couverte
    -0.50
    enzio
    -0.50
    bogen
    -0.50
    POSITIVE LOGITS
     StringVar
    0.80
    Климат
    0.78
     Euripides
    0.72
     otomatig
    0.71
     Shetterly
    0.71
    pleft
    0.70
     للاسماء
    0.70
    abstractmethod
    0.70
     dreamstime
    0.69
    AddTagHelper
    0.69
    Act Density 0.059%

    No Known Activations