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

    Neuronpedia

    INDEX
    Explanations

    references to collaboration and participation in various initiatives or communities

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

    part of something positive

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ivelany
    -0.66
    يميديا
    -0.48
     Мексичка
    -0.48
     iirc
    -0.46
    лтемелер
    -0.44
    ViewImports
    -0.43
     undesirable
    -0.41
     wikipagina
    -0.41
     "¿
    -0.41
     suspiciously
    -0.40
    POSITIVE LOGITS
     such
    0.75
    such
    0.71
     solch
    0.68
     finally
    0.59
    Such
    0.59
    这样一个
    0.59
    这么
    0.58
     چنین
    0.58
     Finally
    0.58
    finally
    0.58
    Act Density 0.026%

    No Known Activations