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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -x
    -0.07
    _battery
    -0.07
     performan
    -0.07
    rip
    -0.06
    .Sp
    -0.06
     dirt
    -0.06
     assay
    -0.06
    -0.06
     IMDb
    -0.06
    .CLIENT
    -0.06
    POSITIVE LOGITS
    estination
    0.07
     ист
    0.07
    braska
    0.07
     روابط
    0.06
    params
    0.06
    depend
    0.06
     pontos
    0.06
    China
    0.06
     pys
    0.06
    particularly
    0.06
    Act Density 0.001%

    No Known Activations