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

    Neuronpedia

    INDEX
    Explanations

    colons

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (th
    -0.07
     dictionary
    -0.07
    œ
    -0.07
    işi
    -0.06
     Т
    -0.06
     nackte
    -0.06
    "h
    -0.06
     ас
    -0.06
     گ
    -0.06
     которое
    -0.06
    POSITIVE LOGITS
    blers
    0.07
     serial
    0.07
    ITH
    0.06
     fragments
    0.06
    قي
    0.06
     earnings
    0.06
     حق
    0.06
     proton
    0.06
     issued
    0.06
     inexp
    0.06
    Act Density 0.101%

    No Known Activations