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

    Neuronpedia

    INDEX
    Explanations

    Short

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    296
    -0.07
     tez
    -0.07
     тоді
    -0.07
     şehir
    -0.06
     Languages
    -0.06
    Để
    -0.06
    _atom
    -0.06
     theoret
    -0.06
    travel
    -0.06
     divor
    -0.06
    POSITIVE LOGITS
    (high
    0.08
    Justin
    0.07
     Justin
    0.07
     초
    0.07
    alie
    0.07
    -red
    0.06
    .Dense
    0.06
    UCE
    0.06
    inta
    0.06
    ATED
    0.06
    Act Density 0.612%

    No Known Activations