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

    Neuronpedia

    INDEX
    Explanations

    4

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     پنج
    -0.07
     Debugger
    -0.06
     Ра
    -0.06
     француз
    -0.06
    ocop
    -0.06
     SIDE
    -0.06
     случае
    -0.06
    eacher
    -0.06
     bàn
    -0.06
     exhibition
    -0.06
    POSITIVE LOGITS
    저
    0.07
    Submit
    0.07
     basal
    0.07
    [cnt
    0.07
     packing
    0.06
    ALLEL
    0.06
    meric
    0.06
    _centers
    0.06
     Laser
    0.06
    ******/↵
    0.06
    Act Density 0.000%

    No Known Activations