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

    Neuronpedia

    INDEX
    Explanations

    on

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .ls
    -0.07
    烤
    -0.07
     rouge
    -0.07
     ordinarily
    -0.06
    НО
    -0.06
     JR
    -0.06
    锿
    -0.06
     телеф
    -0.06
    reira
    -0.06
    ואר
    -0.06
    POSITIVE LOGITS
    궐
    0.07
    봣
    0.06
    significant
    0.06
     participation
    0.06
     "@"
    0.06
    once
    0.06
    ANGLE
    0.06
    덖
    0.06
    生产的
    0.06
     NaN
    0.06
    Act Density 0.018%

    No Known Activations