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

    Neuronpedia

    INDEX
    Explanations

    references to institutions or organizations

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

    profile and default settings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    e
    -0.95
    ee
    -0.78
    eee
    -0.71
    ede
    -0.70
    eeee
    -0.67
    es
    -0.67
    eo
    -0.66
    ei
    -0.66
    eeeee
    -0.66
    ele
    -0.65
    POSITIVE LOGITS
    nya
    0.62
    ness
    0.55
    sin
    0.54
    นะครับ
    0.48
    n
    0.47
    shid
    0.47
    しまった
    0.47
    nment
    0.47
    rij
    0.47
    ron
    0.46
    Act Density 0.038%

    No Known Activations