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

    Neuronpedia

    INDEX
    Explanations

    phrases that describe left and right spatial relationships or asymmetries

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

    "left" or related to the left side

    np_acts-logits-general · gemini-2.0-flash

    direction 'left'

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Autoritní
    -1.11
     nonUne
    -0.85
    SBATCH
    -0.81
    TypedDataSet
    -0.81
     intermédiaire
    -0.80
     nahilalakip
    -0.79
    TintMode
    -0.79
    rawdę
    -0.79
    MENAFN
    -0.78
    dafx
    -0.78
    POSITIVE LOGITS
     Left
    0.82
    LEFT
    0.80
    left
    0.80
     left
    0.79
     LEFT
    0.75
    setLeft
    0.74
    Left
    0.74
     esquerdo
    0.70
    getLeft
    0.66
     Lef
    0.65
    Act Density 0.115%

    No Known Activations