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

    Neuronpedia

    INDEX
    Explanations

    references to dictionaries and encyclopedias

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

    dictionary and spelling

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    IContainer
    -0.52
     برانيه
    -0.47
    SourceChecksum
    -0.47
     viewWillAppear
    -0.47
    ittarius
    -0.45
    Clik
    -0.43
     bahaya
    -0.43
    NVIC
    -0.43
     liggen
    -0.43
    ternut
    -0.43
    POSITIVE LOGITS
     dictionary
    0.80
     dictionaries
    0.73
     Dictionary
    0.69
     autorytatywna
    0.67
     diccionario
    0.61
    dictionary
    0.60
     Wörter
    0.54
    Dictionary
    0.54
     dictionnaire
    0.53
     Dictionaries
    0.52
    Act Density 0.059%

    No Known Activations