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

    Neuronpedia

    INDEX
    Explanations

    numerical data

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    alog
    -0.07
    عة
    -0.06
    .broadcast
    -0.06
     conce
    -0.06
    beg
    -0.06
     bày
    -0.06
    flow
    -0.06
    roll
    -0.06
    Workbook
    -0.06
    ods
    -0.06
    POSITIVE LOGITS
    Uses
    0.07
    [e
    0.06
    	token
    0.06
    (q
    0.06
     applicants
    0.06
     первой
    0.06
    ancouver
    0.06
    	Me
    0.06
    ічні
    0.06
    ічна
    0.06
    Act Density 0.153%

    No Known Activations