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

    Neuronpedia

    INDEX
    Explanations

    references to pairs or dualities

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

    "Two" followed by a noun

    np_acts-logits-general · gemini-2.0-flash

    two followed by multiple

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ly
    -0.65
     algunos
    -0.64
     allemaal
    -0.64
    fully
    -0.63
    algunos
    -0.61
     algunas
    -0.61
     meerdere
    -0.60
     variés
    -0.59
    一个个
    -0.59
     alguno
    -0.58
    POSITIVE LOGITS
     halves
    1.26
     sides
    1.06
    +#+#
    0.94
     opposing
    0.91
     sets
    0.89
     extremes
    0.88
    thirds
    0.85
     separate
    0.84
     main
    0.83
     ends
    0.83
    Act Density 0.284%

    No Known Activations