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

    Neuronpedia

    INDEX
    Explanations

    numerical identifiers related to research publications

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

    `<start_of_turn>user`

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     eventdata
    -0.50
     defaultstate
    -0.44
    typeDefinition
    -0.40
     sää
    -0.39
     Uncategorized
    -0.38
     Ferien
    -0.38
     Aérea
    -0.37
     Grüsse
    -0.37
    Ferien
    -0.37
    buttonShape
    -0.36
    POSITIVE LOGITS
    Tembelea
    0.52
    WriteAttribute
    0.52
    AddTagHelper
    0.52
     насељу
    0.50
    contentLoaded
    0.49
     للمعارف
    0.49
     CreateTagHelper
    0.48
    stylers
    0.47
     PROFILE
    0.46
     صوتيه
    0.46
    Act Density 0.022%

    No Known Activations