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

    Neuronpedia

    INDEX
    Explanations

    Code delimiters

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    OLUM
    -0.08
    որս
    -0.08
     gedeelt
    -0.08
    istel
    -0.08
    ™
    -0.07
    न्द्र
    -0.07
     মন
    -0.07
     saucepan
    -0.07
    ritt
    -0.07
     छै
    -0.07
    POSITIVE LOGITS
    ıyor
    0.08
     Russian
    0.08
    یں
    0.08
     Crud
    0.07
    402
    0.07
     Lessons
    0.07
     critic
    0.07
    jur
    0.07
     Turkish
    0.07
    438
    0.07
    Act Density 0.038%

    No Known Activations