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

    Neuronpedia

    INDEX
    Explanations

    there

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     routing
    -0.07
    _TICK
    -0.06
     EXPRESS
    -0.06
    ("[%
    -0.06
     Cultural
    -0.06
    Pay
    -0.06
     프로
    -0.06
    /t
    -0.06
     Formats
    -0.06
     complains
    -0.06
    POSITIVE LOGITS
    elerik
    0.07
    ندا
    0.07
     потрап
    0.07
    hya
    0.07
    —you
    0.06
     etraf
    0.06
     유형
    0.06
    ;(
    0.06
    urahan
    0.06
     hospitalized
    0.06
    Act Density 0.015%

    No Known Activations