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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating uncertainty or vagueness about specific characteristics or classifications

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

    some [type/instance]

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     uwagę
    -0.50
    paravant
    -0.42
    はじめに
    -0.41
     dentaire
    -0.41
     marié
    -0.41
    Bakgrunnsstoff
    -0.38
     nemlig
    -0.37
     prestazioni
    -0.36
     ponts
    -0.36
    Facades
    -0.36
    POSITIVE LOGITS
     algún
    0.85
     algum
    0.79
     irgende
    0.79
     alguma
    0.77
     somewhere
    0.77
     someplace
    0.73
     alguna
    0.73
     Somewhere
    0.72
     something
    0.71
     algun
    0.69
    Act Density 0.076%

    No Known Activations