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

    Neuronpedia

    INDEX
    Explanations

    parameters arguments

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    आ
    -0.07
    £o
    -0.07
    睛
    -0.06
    hift
    -0.06
    弹
    -0.06
     hypertension
    -0.06
     males
    -0.06
     standardized
    -0.06
    ρου
    -0.06
    io
    -0.06
    POSITIVE LOGITS
    oggle
    0.07
     Lil
    0.06
     implode
    0.06
    0.06
    ूड
    0.06
    ')))
    0.06
     Lorem
    0.06
     christmas
    0.06
     alum
    0.06
     Oregon
    0.06
    Act Density 0.024%

    No Known Activations