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

    Neuronpedia

    INDEX
    Explanations

    labels and titles for different entities and concepts within various contexts

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

    naming and labeling

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ✭✭
    -0.41
     rapport
    -0.34
     BoxFit
    -0.34
    toBeTruthy
    -0.34
    arm
    -0.34
    évaluateur
    -0.33
    Życiorys
    -0.33
     stick
    -0.32
     useRouter
    -0.30
     Pristupljeno
    -0.30
    POSITIVE LOGITS
    хьтан
    0.64
     ModelExpression
    0.60
     ujednoznacz
    0.57
     kaarangay
    0.55
     transfieras
    0.54
     ErrIntOverflow
    0.47
    ffilm
    0.46
     الحره
    0.46
     pinulongan
    0.46
    BorderFactory
    0.45
    Act Density 0.055%

    No Known Activations