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

    Neuronpedia

    INDEX
    Explanations

    computer cursor/UI changes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    recent
    -0.08
     exponentially
    -0.08
    _recent
    -0.07
     introduce
    -0.07
     expliqu
    -0.07
    Dol
    -0.07
    _reduce
    -0.07
    bins
    -0.07
    -story
    -0.07
    ember
    -0.07
    POSITIVE LOGITS
    	cursor
    0.10
     Cursor
    0.10
    .Cursor
    0.10
    (Cursor
    0.10
    .Cursors
    0.10
     arrows
    0.10
    Cursor
    0.09
     చూప
    0.09
     cursor
    0.09
     стрел
    0.09
    Act Density 0.001%

    No Known Activations