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

    Neuronpedia

    INDEX
    Explanations

    is

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (Data
    -0.06
     cpu
    -0.06
    Weights
    -0.06
     fig
    -0.06
    TableView
    -0.06
    .reward
    -0.06
    	description
    -0.06
    	write
    -0.06
    	animation
    -0.06
     expected
    -0.06
    POSITIVE LOGITS
    ти
    0.06
    933
    0.06
    _glob
    0.06
    tuğ
    0.06
    uspend
    0.06
     Maj
    0.06
     Quit
    0.06
     earliest
    0.06
     Buck
    0.06
     disag
    0.06
    Act Density 0.057%

    No Known Activations