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

    Neuronpedia

    INDEX
    Explanations

    probability, explanation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    éfono
    -0.08
    ptoms
    -0.08
    mail
    -0.07
    کار
    -0.06
    cu
    -0.06
    -------
    -0.06
    xis
    -0.06
     tearDown
    -0.06
    Turn
    -0.06
    atırım
    -0.06
    POSITIVE LOGITS
     aperture
    0.07
     лі
    0.07
     Jaw
    0.07
    URATION
    0.07
     Coy
    0.06
     nev
    0.06
     YE
    0.06
    =R
    0.06
     plung
    0.06
     Rockets
    0.06
    Act Density 0.067%

    No Known Activations