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

    Neuronpedia

    INDEX
    Explanations

    the of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    학교
    -0.08
     delimited
    -0.07
    .Focus
    -0.07
     calibration
    -0.07
    ctest
    -0.06
    ypical
    -0.06
     Fantasy
    -0.06
    url
    -0.06
    	dx
    -0.06
    lf
    -0.06
    POSITIVE LOGITS
     theorists
    0.06
     사람은
    0.06
    /operator
    0.06
                                  ↵
    0.06
    Zoom
    0.06
    _program
    0.06
    .BO
    0.06
    267
    0.06
    /S
    0.06
    ๐
    0.06
    Act Density 0.039%

    No Known Activations