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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    dikleri
    -0.07
     prv
    -0.07
     выбор
    -0.06
    ại
    -0.06
    нож
    -0.06
    ปกครอง
    -0.06
    landır
    -0.06
    对于
    -0.06
    Highlighted
    -0.06
    	Service
    -0.06
    POSITIVE LOGITS
    ances
    0.08
    Á
    0.06
     MST
    0.06
     NST
    0.06
    .tables
    0.06
     kamp
    0.06
    levator
    0.06
    istema
    0.06
    haar
    0.06
    طح
    0.06
    Act Density 0.518%

    No Known Activations