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

    Neuronpedia

    INDEX
    Explanations

    phrases related to justifications or explanations for actions and decisions

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

    explaining many reasons

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     autorytatywna
    -0.61
    FormTagHelper
    -0.57
    #+#
    -0.53
    GOTREF
    -0.53
    pushFollow
    -0.50
    Personendaten
    -0.48
     المعيارى
    -0.48
     configureStore
    -0.48
    findpost
    -0.46
    OGND
    -0.46
    POSITIVE LOGITS
     vieles
    0.58
     архивлан
    0.50
    様々な
    0.50
    さまざまな
    0.50
     many
    0.48
     birçok
    0.45
     Many
    0.44
     berbagai
    0.44
     wiele
    0.44
     nombreuses
    0.43
    Act Density 0.289%

    No Known Activations