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

    Neuronpedia

    INDEX
    Explanations

    key

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     religions
    -0.08
     môn
    -0.06
    LECTION
    -0.06
     Tribune
    -0.06
    dal
    -0.06
     Blank
    -0.06
    あげ
    -0.06
     sàn
    -0.06
    @section
    -0.06
     dernière
    -0.06
    POSITIVE LOGITS
    cole
    0.07
     vaccinations
    0.06
    235
    0.06
    ců
    0.06
     interpreter
    0.06
    ورد
    0.06
    Direct
    0.06
     použít
    0.06
    urry
    0.06
     Int
    0.06
    Act Density 0.000%

    No Known Activations