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

    Neuronpedia

    INDEX
    Explanations

    contexts involving positioning or placement beneath or below objects or surfaces

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

    under or bottom position

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    fastjson
    -0.50
    tonsoft
    -0.46
    onAttach
    -0.45
     Efq
    -0.45
    MVH
    -0.44
     continúas
    -0.43
    jsonwebtoken
    -0.43
    ⋙
    -0.43
     bouquets
    -0.42
     createSlice
    -0.42
    POSITIVE LOGITS
     bottom
    0.70
     underneath
    0.68
     Bottom
    0.67
    Bottom
    0.63
     BOTTOM
    0.61
     bottoms
    0.60
     beneath
    0.60
    底
    0.59
    bottom
    0.57
     floor
    0.57
    Act Density 0.059%

    No Known Activations