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

    Neuronpedia

    INDEX
    Explanations

    TestCase

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Ziel
    -0.07
     blat
    -0.07
     پسر
    -0.06
    galement
    -0.06
     nejen
    -0.06
     bour
    -0.06
    ?,
    -0.06
    .dsl
    -0.06
     Giovanni
    -0.06
     Бер
    -0.06
    POSITIVE LOGITS
    TestCase
    0.10
    .TestCase
    0.09
    режд
    0.07
     SHARES
    0.07
    (TestCase
    0.06
     TestCase
    0.06
    sql
    0.06
     earthquake
    0.06
    _unregister
    0.06
    _TestCase
    0.06
    Act Density 0.002%

    No Known Activations