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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     مکان
    -0.06
     FRA
    -0.06
     graves
    -0.06
    ray
    -0.06
    zon
    -0.06
    _sphere
    -0.06
     sedm
    -0.06
     yararlan
    -0.06
    دار
    -0.06
    Editor
    -0.06
    POSITIVE LOGITS
    ="${
    0.07
     DIS
    0.07
     vc
    0.07
     εισ
    0.07
    esign
    0.06
    Sign
    0.06
     clears
    0.06
    mods
    0.06
     CUDA
    0.06
    .Reset
    0.06
    Act Density 0.096%

    No Known Activations