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

    Neuronpedia

    INDEX
    Explanations

    scientific terms

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     thankful
    -0.07
     Pamela
    -0.06
     تنها
    -0.06
     U
    -0.06
     Jah
    -0.06
     presidential
    -0.06
    Due
    -0.06
     quiz
    -0.06
    ventory
    -0.06
     Ook
    -0.06
    POSITIVE LOGITS
     Implicit
    0.07
     native
    0.06
     sizing
    0.06
    プロ
    0.06
    ักส
    0.06
    fil
    0.06
    ryo
    0.06
    θεση
    0.06
     گرم
    0.06
    (Locale
    0.06
    Act Density 0.015%

    No Known Activations