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

    Neuronpedia

    INDEX
    Explanations

    instructions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _US
    -0.06
     фото
    -0.06
    .Ribbon
    -0.06
     psychiat
    -0.06
     psychiatric
    -0.06
     Psychiat
    -0.06
     historian
    -0.06
    áž
    -0.06
     Roulette
    -0.06
     astronomy
    -0.06
    POSITIVE LOGITS
    有点
    0.06
    ＿_
    0.06
    ___
    0.06
     nap
    0.06
     هایی
    0.06
     Rangers
    0.06
    รรค
    0.05
    ##_
    0.05
     în
    0.05
     clk
    0.05
    Act Density 0.024%

    No Known Activations