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

    Neuronpedia

    INDEX
    Explanations

    comments in a code or markup format

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

    Roman or numerical representation of numbers

    np_acts-logits-general · gemini-2.0-flash

    seventh, VII

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Abraham
    -0.51
    지
    -0.47
    enser
    -0.46
     associate
    -0.46
     Narrow
    -0.45
     narrow
    -0.44
    geslacht
    -0.44
     stretcher
    -0.44
    narrow
    -0.44
     Fame
    -0.43
    POSITIVE LOGITS
        
    1.07
     seventh
    1.01
     متعلقه
    0.99
     VII
    0.94
     seven
    0.93
    VII
    0.92
    seventh
    0.90
     Seventh
    0.89
     SEVENTH
    0.88
    Seventh
    0.88
    Act Density 0.235%

    No Known Activations