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

    Neuronpedia

    INDEX
    Explanations

    phrases related to positioning or positional terminology

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

    "position" or its variations

    np_acts-logits-general · gemini-2.0-flash

    position and positional terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     autorytatywna
    -0.84
     Fet
    -0.70
    WebVitals
    -0.70
     Мексичка
    -0.67
    ImageContext
    -0.67
     snippetHide
    -0.66
    helves
    -0.65
     дописавши
    -0.65
     móc
    -0.64
    DeleteBehavior
    -0.63
    POSITIVE LOGITS
     positions
    0.90
     pos
    0.82
     position
    0.78
     Position
    0.76
     Pos
    0.75
    Positions
    0.75
    posit
    0.73
     Positions
    0.72
     getPosition
    0.71
     POSITION
    0.69
    Act Density 0.278%

    No Known Activations