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

    Neuronpedia

    INDEX
    Explanations

    references to individual items or instances

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

    each noun

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    endphp
    -0.66
     kaarangay
    -0.63
    <unused51>
    -0.60
    <unused1>
    -0.60
    𑄣
    -0.60
    [@BOS@]
    -0.60
    <unused3>
    -0.60
    <unused55>
    -0.60
    bildtitel
    -0.60
    <unused7>
    -0.59
    POSITIVE LOGITS
     these
    0.33
     Lingkungan
    0.32
     CreateTagHelper
    0.30
     Komunikasi
    0.30
    AndEndTag
    0.29
     chrétien
    0.28
     Pembangunan
    0.28
     navideño
    0.28
     contactez
    0.28
     those
    0.28
    Act Density 0.055%

    No Known Activations