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

    Neuronpedia

    INDEX
    Explanations

    methods and instructional content related to processes

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

    mathematical notation and foreign words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    IntoConstraints
    -0.75
     صوتيه
    -0.74
     invokingState
    -0.73
     Normdatei
    -0.71
    StructEnd
    -0.70
     lenker
    -0.68
     للمعارف
    -0.66
     يتيمه
    -0.66
     FetchType
    -0.66
    NameInMap
    -0.65
    POSITIVE LOGITS
     piacere
    0.35
     fournies
    0.34
     erleben
    0.33
    endaft
    0.33
     tetap
    0.33
     confirmar
    0.32
     gespannt
    0.32
     Vergnügen
    0.32
     sogno
    0.32
     húmedo
    0.31
    Act Density 0.035%

    No Known Activations