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

    Neuronpedia

    INDEX
    Explanations

    numerical data and references in scientific or technical documents

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

    numbers and colons

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ویکی‌پدی
    -0.57
     Svensson
    -0.38
    XmlAccessType
    -0.36
     inderdaad
    -0.34
     Domínguez
    -0.34
     Vázquez
    -0.34
     Gefühl
    -0.33
    RTEE
    -0.33
    LookAnd
    -0.32
     Decke
    -0.32
    POSITIVE LOGITS
    rungsseite
    0.83
     zwiſchen
    0.80
    niſſe
    0.79
    <unused51>
    0.77
    <unused41>
    0.77
    <unused14>
    0.77
    <unused8>
    0.77
    <unused28>
    0.77
    <unused3>
    0.77
    [@BOS@]
    0.77
    Act Density 0.047%

    No Known Activations