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

    Neuronpedia

    INDEX
    Explanations

    terms related to data privacy and security practices

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

    legal and ethical purposes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Sm
    -0.52
     sm
    -0.46
    Sm
    -0.45
     strange
    -0.43
     Mer
    -0.42
    oids
    -0.42
     MB
    -0.41
     bode
    -0.41
     serial
    -0.41
    ante
    -0.40
    POSITIVE LOGITS
     propOrder
    0.66
     MainAxisSize
    0.54
    niająca
    0.50
     Privacidad
    0.47
     westfalen
    0.47
    الحياه
    0.47
     Garantía
    0.46
    instancetype
    0.46
     actualidad
    0.46
     Grüsse
    0.44
    Act Density 0.004%

    No Known Activations