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

    Neuronpedia

    INDEX
    Explanations

    concepts related to morality and societal values

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

    values, ideals, principles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     مواليد
    -0.42
    rasing
    -0.40
     Periods
    -0.39
     rhestr
    -0.39
    loyment
    -0.39
     CURLOPT
    -0.39
    Historio
    -0.38
    lasts
    -0.37
     Saul
    -0.37
     Ethan
    -0.36
    POSITIVE LOGITS
     unknownFields
    0.59
     values
    0.53
     valeurs
    0.53
     valori
    0.47
     valores
    0.44
    Values
    0.43
    rungsseite
    0.41
    Valores
    0.41
     Werte
    0.41
    RenderAtEndOf
    0.40
    Act Density 0.090%

    No Known Activations