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

    Neuronpedia

    INDEX
    Explanations

    vertical movement

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    getImageFolder
    0.52
     الهدف
    0.47
     السالب
    0.45
    isOnTimer
    0.45
    dout
    0.43
    akra
    0.43
    MAF
    0.42
     Quadrup
    0.42
     Länder
    0.42
     சூ
    0.41
    POSITIVE LOGITS
     stairs
    0.76
     ladder
    0.70
     лест
    0.68
     hill
    0.67
     staircase
    0.62
     ladders
    0.61
    坂
    0.59
     stairway
    0.57
     strada
    0.56
     hillside
    0.56
    Act Density 0.021%

    No Known Activations