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

    Neuronpedia

    INDEX
    Explanations

    punctuation/filler words

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    šti
    -0.07
    iets
    -0.07
    YTE
    -0.07
    ichtig
    -0.06
    563
    -0.06
    ovo
    -0.06
    73
    -0.06
    inka
    -0.06
    IVE
    -0.06
    768
    -0.06
    POSITIVE LOGITS
    (gl
    0.07
     Beans
    0.07
    .openConnection
    0.07
     又
    0.06
    otionEvent
    0.06
     athleticism
    0.06
     geniş
    0.06
    	socket
    0.06
    (CG
    0.06
    .INFO
    0.06
    Act Density 0.023%

    No Known Activations