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

    Neuronpedia

    INDEX
    Explanations

    square root calculation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Proble
    0.43
    Software
    0.42
     Scanner
    0.40
     Finger
    0.40
     člán
    0.40
    介绍了
    0.38
     Sensor
    0.37
    Cock
    0.37
     Britannica
    0.37
    ESI
    0.37
    POSITIVE LOGITS
     bidders
    0.47
    dwm
    0.45
     wynosi
    0.45
    iul
    0.45
    IFUL
    0.45
    rown
    0.43
     EDGE
    0.43
     personne
    0.43
    frow
    0.43
    ಜನ
    0.42
    Act Density 0.001%

    No Known Activations