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

    Neuronpedia

    INDEX
    Explanations

    phrases related to significant actions or events

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

    action while

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    RenderAtEndOf
    -0.41
     vœux
    -0.40
    ukses
    -0.40
     gethan
    -0.40
     bluzka
    -0.40
     Cliquez
    -0.38
     asamblea
    -0.36
     lecteurs
    -0.36
     heridos
    -0.36
     resourceCulture
    -0.36
    POSITIVE LOGITS
    bkz
    0.50
    TargetApi
    0.49
    RegressionTest
    0.49
     swag
    0.45
    etration
    0.45
     beauties
    0.43
    ppin
    0.43
     Motif
    0.43
     potr
    0.42
    hashtags
    0.41
    Act Density 0.157%

    No Known Activations