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

    Neuronpedia

    INDEX
    Explanations

    addressing a group

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     doodles
    0.57
     blobs
    0.56
     info
    0.53
     blob
    0.53
     combo
    0.53
     cranks
    0.53
     gooey
    0.52
     leftover
    0.52
    +
    0.52
     disk
    0.52
    POSITIVE LOGITS
     여러분
    0.86
     yourselves
    0.83
     our
    0.82
     hepin
    0.81
     আপনাদের
    0.80
     nossa
    0.80
     আমরা
    0.79
     ನಮ್ಮ
    0.79
     нашего
    0.79
    你們
    0.79
    Act Density 0.093%

    No Known Activations