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

    Neuronpedia

    INDEX
    Explanations

    diagram lines

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     culpa
    -0.07
    Sold
    -0.06
    $list
    -0.06
    ijk
    -0.06
    -col
    -0.06
     강남
    -0.06
    Gram
    -0.06
    Beat
    -0.06
    rán
    -0.06
    	camera
    -0.06
    POSITIVE LOGITS
    160
    0.08
    เม
    0.07
    電話
    0.07
    ogenerated
    0.06
    кое
    0.06
    (fake
    0.06
     Calculates
    0.06
    (setting
    0.06
    IGHL
    0.06
    THEN
    0.06
    Act Density 0.001%

    No Known Activations