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

    Neuronpedia

    INDEX
    Explanations

    code snippets in various languages

    oai_token-act-pair · gemini-2.0-flash

    code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Ko
    -0.49
     N
    -0.45
     S
    -0.44
     Related
    -0.44
     Pe
    -0.43
     F
    -0.43
     inc
    -0.43
    不着
    -0.43
     M
    -0.43
    Related
    -0.43
    POSITIVE LOGITS
    tagHelperRunner
    0.70
     تضيفلها
    0.65
     Drapeau
    0.63
    出版年
    0.62
     anhydride
    0.61
    (!__
    0.60
     Gladiator
    0.60
     للاسماء
    0.60
     يتيمه
    0.60
     Ferdinando
    0.60
    Act Density 4.218%

    No Known Activations