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

    Neuronpedia

    INDEX
    Explanations

    text formatting or structural elements in documents

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

    Non-alphanumeric characters

    np_acts-logits-general · gemini-2.0-flash

    visual separators

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     FetchType
    -0.83
     Ανακτήθηκε
    -0.81
    клопе
    -0.73
    Véxase
    -0.72
     незавершена
    -0.71
    NewReader
    -0.70
     насељу
    -0.69
     consultato
    -0.69
    MLLoader
    -0.69
     AssemblyVersion
    -0.68
    POSITIVE LOGITS
    ↵↵
    0.57
     materialism
    0.51
     inoxidable
    0.51
    ↵
    0.50
    tez
    0.49
     felicity
    0.47
    Vader
    0.47
     Extern
    0.45
    évaluateur
    0.45
     impeller
    0.44
    Act Density 0.362%

    No Known Activations