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

    Neuronpedia

    INDEX
    Explanations

    references to Afghan-related terms and waveforms in a technical context

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

    waveform generation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    SpringBootTest
    -0.49
    rdom
    -0.49
    LLocation
    -0.48
    IInter
    -0.47
    atism
    -0.46
    itarianism
    -0.45
     Waterman
    -0.45
     $("
    -0.44
    cising
    -0.44
    riman
    -0.43
    POSITIVE LOGITS
     Afghan
    0.88
    Afghan
    0.75
     Afghans
    0.67
     Exacts
    0.61
    fieurs
    0.56
     Jules
    0.56
    ientras
    0.55
     protoimpl
    0.54
     Houſe
    0.53
    <mask>
    0.51
    Act Density 0.012%

    No Known Activations