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

    Neuronpedia

    INDEX
    Explanations

    key entities and their relationships in structured data descriptions

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

    each [noun]

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    pkey
    -0.49
     disposed
    -0.46
     not
    -0.45
     no
    -0.43
     low
    -0.42
     long
    -0.42
     very
    -0.41
     Alpha
    -0.41
    참고
    -0.41
     patent
    -0.41
    POSITIVE LOGITS
    Each
    0.66
    Every
    0.65
    Chaque
    0.65
     Jedes
    0.64
    Setiap
    0.64
     Chaque
    0.63
     ognuno
    0.63
     Each
    0.63
     Every
    0.62
    Ogni
    0.62
    Act Density 0.103%

    No Known Activations