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

    Neuronpedia

    INDEX
    Explanations

    technical/mathematical

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    +#+#
    -0.71
     Meksiku
    -0.64
    ArgsConstructor
    -0.61
     autorytatywna
    -0.60
    UnusedPrivate
    -0.60
     سكانية
    -0.58
    Javadoc
    -0.56
    viewDidLoad
    -0.56
     &___
    -0.56
     betweenstory
    -0.55
    POSITIVE LOGITS
    komp
    0.57
     transform
    0.52
     filter
    0.50
    นน
    0.49
     Tilt
    0.48
     Filtered
    0.48
     Forth
    0.46
     filtering
    0.46
    거
    0.45
     gri
    0.44
    Act Density 0.001%

    No Known Activations