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

    Neuronpedia

    INDEX
    Explanations

    programming scripts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ables
    -0.07
    Other
    -0.07
    882
    -0.06
     thyroid
    -0.06
    (Grid
    -0.06
     ################################################
    -0.06
     yaş
    -0.06
     یافت
    -0.06
     sap
    -0.06
     Nex
    -0.06
    POSITIVE LOGITS
    ρον
    0.07
     silently
    0.06
     fury
    0.06
    ±ظ
    0.06
     POINTER
    0.06
    moving
    0.06
    ��
    0.06
     Axe
    0.06
    oliday
    0.06
     Exposure
    0.06
    Act Density 0.012%

    No Known Activations