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

    Neuronpedia

    INDEX
    Explanations

    a mix of past tense verbs and Croatian words

    oai_token-act-pair · gemini-2.0-flash

    unique identifiers or names

    np_token-act-pair-logits · gpt-4o-mini

    Foreign languages and code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    LayoutStyle
    -0.52
    })`
    -0.50
    Geplaatst
    -0.46
    PARATUS
    -0.46
    σθαι
    -0.46
    pexpr
    -0.45
     étoile
    -0.44
    дачи
    -0.44
    `),
    -0.44
     déco
    -0.43
    POSITIVE LOGITS
     مشين
    0.69
    }\\
    0.67
     lenker
    0.61
    ven
    0.59
    Gener
    0.59
    rouwen
    0.58
    brainly
    0.58
    ValueStyle
    0.57
    Ven
    0.57
    )\\
    0.56
    Act Density 0.214%

    No Known Activations