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

    Neuronpedia

    INDEX
    Explanations

    scientific notation and specific sequences or patterns of characters used in technical contexts

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

    mathematical expressions with symbols

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    urut
    -0.43
     plufieurs
    -0.37
    loroethane
    -0.36
    ificacion
    -0.36
    rophes
    -0.36
     asamblea
    -0.34
    koon
    -0.34
     anún
    -0.34
    hadas
    -0.34
     rechange
    -0.34
    POSITIVE LOGITS
     ivelany
    0.73
     Савезне
    0.65
     Мексичка
    0.64
    Parcelize
    0.63
    CppMethod
    0.61
    IndentedString
    0.60
    Хьажоргаш
    0.55
    хьтан
    0.53
     Италијани
    0.53
     '\\;'
    0.52
    Act Density 1.018%

    No Known Activations