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

    Neuronpedia

    INDEX
    Explanations

    they

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     угод
    -0.06
     Wake
    -0.06
    争
    -0.06
     เง
    -0.06
    ctr
    -0.06
     alley
    -0.06
    Demo
    -0.06
    $date
    -0.06
     Mirror
    -0.06
     fault
    -0.06
    POSITIVE LOGITS
    599
    0.07
    arı
    0.07
    .interpolate
    0.06
    leasing
    0.06
    .verify
    0.06
     adidas
    0.06
     dreaming
    0.06
    83
    0.06
    \":
    0.06
    /Common
    0.06
    Act Density 0.001%

    No Known Activations