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

    Neuronpedia

    INDEX
    Explanations

    mathematical notation and formal definitions

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

    Mathematical or logical conditions/statements

    np_acts-logits-general · gemini-2.0-flash

    if and only if

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    прочем
    -0.58
     respons
    -0.51
     Emphas
    -0.50
    ++);
    -0.48
    &)
    -0.46
    摩
    -0.46
     traz
    -0.45
    iy
    -0.44
     bezeichneter
    -0.43
    *}{
    -0.43
    POSITIVE LOGITS
     there
    0.90
    InjectAttribute
    0.81
     esistono
    0.79
    either
    0.78
    Either
    0.78
     esiste
    0.77
     Either
    0.77
     either
    0.75
     CreateTagHelper
    0.75
     существует
    0.73
    Act Density 1.491%

    No Known Activations