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

    Neuronpedia

    INDEX
    Explanations

    good

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     differ
    -0.07
    -L
    -0.07
    urile
    -0.06
     Japanese
    -0.06
    few
    -0.06
     MH
    -0.06
     вим
    -0.06
    535
    -0.06
     Thánh
    -0.06
     gram
    -0.06
    POSITIVE LOGITS
    Reg
    0.07
    esa
    0.06
     forCellReuseIdentifier
    0.06
    _deg
    0.06
    ника
    0.06
     robber
    0.06
     졸
    0.06
     '\\'
    0.06
    [start
    0.06
    .rotate
    0.06
    Act Density 0.008%

    No Known Activations