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

    Neuronpedia

    INDEX
    Explanations

    elements related to user interface design in coding contexts

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

    alloc new Object

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    AndEndTag
    -0.91
    دانشنامهٔ
    -0.75
     estekak
    -0.72
    expandindo
    -0.68
    RegressionTest
    -0.66
    GEBURTSDATUM
    -0.66
     ویکی‌پدی
    -0.62
     utafitiHapana
    -0.59
     pinulongan
    -0.59
     queſta
    -0.58
    POSITIVE LOGITS
     libremente
    0.35
     chimiques
    0.35
     larmes
    0.34
     Paglinawan
    0.34
     chimique
    0.34
     defaultstate
    0.33
     femininas
    0.33
     orgánico
    0.33
     hablado
    0.32
     leggi
    0.31
    Act Density 0.656%

    No Known Activations