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

    Neuronpedia

    INDEX
    Explanations

    unsigned

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    xaf
    -0.07
     למנ
    -0.07
    isen
    -0.07
     niños
    -0.07
     Pit
    -0.06
    PrimaryKey
    -0.06
    hänge
    -0.06
    uxtap
    -0.06
    Ak
    -0.06
     AN
    -0.06
    POSITIVE LOGITS
     longevity
    0.08
    💤
    0.08
     sane
    0.08
     Sect
    0.08
    _passed
    0.07
    _bug
    0.07
    _soup
    0.07
    ῆ
    0.07
    الة
    0.07
     PDO
    0.07
    Act Density 0.002%

    No Known Activations