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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     evaluation
    -0.07
     Dodd
    -0.06
     Evaluation
    -0.06
     Rpc
    -0.06
    TRA
    -0.06
    _shape
    -0.06
    (di
    -0.06
    _drv
    -0.06
     dbg
    -0.06
     backgroundImage
    -0.06
    POSITIVE LOGITS
    му
    0.07
     giảng
    0.07
    裕
    0.06
     initWithTitle
    0.06
     않고
    0.06
    �
    0.06
    ilton
    0.06
    케이
    0.06
    ěst
    0.06
     �
    0.06
    Act Density 0.015%

    No Known Activations