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

    Neuronpedia

    INDEX
    Explanations

    asked

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    minute
    -0.07
     น
    -0.06
     illustrations
    -0.06
     fiction
    -0.06
    does
    -0.06
     revolutions
    -0.06
     occur
    -0.06
     stol
    -0.06
     DEVELO
    -0.06
    ować
    -0.06
    POSITIVE LOGITS
    ************************************************
    0.07
    ний
    0.06
    -camera
    0.06
    rms
    0.06
    膜
    0.06
     race
    0.06
     emptied
    0.06
    'am
    0.06
    ettings
    0.06
    _heading
    0.06
    Act Density 0.012%

    No Known Activations