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

    Neuronpedia

    INDEX
    Explanations

    proper nouns, particularly names of people and organizations

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

    names after "both" or "respectively"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     and
    -0.65
    性和
    -0.63
    力和
    -0.59
    Ecotoxicity
    -0.54
    子和
    -0.49
     noDo
    -0.48
    人和
    -0.43
    المناصب
    -0.42
    rungsseite
    -0.41
     كومونز
    -0.40
    POSITIVE LOGITS
     respectively
    0.68
     begge
    0.66
     respectivamente
    0.66
     alike
    0.62
     ambos
    0.59
     keduanya
    0.56
     båda
    0.56
    Ambos
    0.55
    respectively
    0.54
     दोनों
    0.53
    Act Density 0.127%

    No Known Activations