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

    Neuronpedia

    INDEX
    Explanations

    Numbers in technical descriptions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     sáng
    -0.07
    Floating
    -0.07
    ingt
    -0.07
    inct
    -0.07
    Expected
    -0.06
    -cost
    -0.06
    _parts
    -0.06
     OST
    -0.06
    Bus
    -0.06
     церк
    -0.06
    POSITIVE LOGITS
     LOVE
    0.06
              ↵
    0.06
    0.06
     IPCC
    0.06
         ↵
    0.06
     э
    0.06
    ुलन
    0.06
     بان
    0.06
    ガ
    0.06
     لازم
    0.06
    Act Density 0.021%

    No Known Activations