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

    Neuronpedia

    INDEX
    Explanations

    phrases referring to advantages, benefits, and features of a concept or product

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

    Positive or negative qualities/features

    np_acts-logits-general · gemini-2.0-flash

    specific characteristic or quality

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     thither
    -0.75
     createState
    -0.72
    évaluateur
    -0.71
    msgTypes
    -0.66
    icksburg
    -0.62
    værende
    -0.59
     stiefel
    -0.59
    ISTICAL
    -0.58
     مشين
    -0.57
    hdessä
    -0.56
    POSITIVE LOGITS
     assumption
    0.64
     cherchés
    0.56
    formik
    0.55
     aim
    0.55
     idea
    0.54
     notion
    0.54
    fet
    0.53
     task
    0.51
     option
    0.49
    ungkinkan
    0.49
    Act Density 0.417%

    No Known Activations