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

    Neuronpedia

    INDEX
    Explanations

    adjectives expressing a positive sentiment or an observation of beauty

    oai_token-act-pair · gemini-2.0-flash

    beauty

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     <=",
    -0.62
     nulle
    -0.56
    AddTagHelper
    -0.56
     ModelExpression
    -0.54
     للمعارف
    -0.54
     typelib
    -0.54
    dited
    -0.52
    تمع
    -0.50
    yntaxException
    -0.50
    تفصیلات
    -0.49
    POSITIVE LOGITS
    లాలు
    0.54
    clable
    0.54
    Handlung
    0.53
    दार
    0.51
    EEN
    0.49
    '],
    0.49
     endforeach
    0.49
    `,
    0.49
    bewerken
    0.49
    '):
    0.49
    Act Density 0.208%

    No Known Activations