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

    Neuronpedia

    INDEX
    Explanations

    keyboard input event handling

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Feedback
    0.42
    Radial
    0.41
    𒈾
    0.41
    MIDI
    0.41
    舀
    0.40
    盛
    0.40
    势
    0.40
    粒子
    0.40
    Jumlah
    0.39
    指
    0.39
    POSITIVE LOGITS
     up
    0.42
    UP
    0.41
     left
    0.41
     Space
    0.40
    space
    0.40
     fre
    0.39
     Polar
    0.39
     s
    0.38
    adan
    0.38
     Arrow
    0.38
    Act Density 0.008%

    No Known Activations