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

    Neuronpedia

    INDEX
    Explanations

    Cells and glands

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     рекомендуется
    -0.07
    covers
    -0.07
     stable
    -0.06
     Stable
    -0.06
     گردید
    -0.06
    بية
    -0.06
     downfall
    -0.06
     SharedModule
    -0.06
     PHY
    -0.06
    ذیر
    -0.06
    POSITIVE LOGITS
     İç
    0.07
    μι
    0.07
    _SL
    0.06
    侵
    0.06
    �
    0.06
    PEND
    0.06
     hav
    0.06
     discrim
    0.06
    oldown
    0.06
    持
    0.06
    Act Density 0.019%

    No Known Activations