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

    Neuronpedia

    INDEX
    Explanations

    what/which

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Trudeau
    -0.07
    فل
    -0.07
    iens
    -0.06
     Hwy
    -0.06
    amon
    -0.06
    -k
    -0.06
     Maz
    -0.06
    وک
    -0.06
    blade
    -0.06
    θεν
    -0.06
    POSITIVE LOGITS
    viders
    0.07
     arab
    0.07
    lanmıştır
    0.06
     şekil
    0.06
    :model
    0.06
     draft
    0.06
     وزار
    0.06
    $field
    0.06
     Territories
    0.06
     गत
    0.06
    Act Density 0.062%

    No Known Activations