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

    Neuronpedia

    INDEX
    Explanations

    Code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     interruption
    -0.07
     مرة
    -0.07
     행복
    -0.06
    lant
    -0.06
    iciary
    -0.06
     hỗn
    -0.06
    _timeline
    -0.06
    owners
    -0.06
    _COUNTRY
    -0.06
    .localtime
    -0.06
    POSITIVE LOGITS
     annonce
    0.07
    _finalize
    0.07
     till
    0.06
    实现
    0.06
    Als
    0.06
     suppressing
    0.06
    610
    0.06
     rej
    0.06
     dissert
    0.06
    _TestCase
    0.06
    Act Density 0.231%

    No Known Activations