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

    Neuronpedia

    INDEX
    Explanations

    foreign words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _some
    -0.06
    _pin
    -0.06
     muttered
    -0.06
    .HasPrefix
    -0.06
    yi
    -0.06
     навер
    -0.06
    .Net
    -0.06
    quel
    -0.06
     Hyundai
    -0.06
     USERS
    -0.06
    POSITIVE LOGITS
     през
    0.07
     réal
    0.07
    งน
    0.07
    rå
    0.06
    icamente
    0.06
    ص
    0.06
     เง
    0.06
    �n
    0.06
     restricting
    0.06
     конт
    0.06
    Act Density 0.000%

    No Known Activations