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

    Neuronpedia

    INDEX
    Explanations

    code-related syntax and structure, particularly involving coordinates and geometric properties

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Code involving offsets or height measurements

    np_acts-logits-general · gemini-2.0-flash

    vertical position or height

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    drawSprites
    -0.51
     male
    -0.50
    GetX
    -0.47
    clientWidth
    -0.46
     Mr
    -0.46
    Geographie
    -0.45
    centerX
    -0.44
    řevě
    -0.44
     Michael
    -0.44
     Male
    -0.43
    POSITIVE LOGITS
     height
    1.05
     translateY
    1.04
    setVerticalGroup
    0.97
     mouseY
    0.95
     HEIGHT
    0.93
     heights
    0.91
     Height
    0.91
    height
    0.88
     getHeight
    0.87
     women
    0.86
    Act Density 0.532%

    No Known Activations