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

    Neuronpedia

    INDEX
    Explanations

    symbols and special characters in the text

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

    does nothing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    strado
    -0.36
    ElementAt
    -0.34
     جر
    -0.33
     Glück
    -0.32
    zelfde
    -0.32
     Sehingga
    -0.29
     Bezirk
    -0.29
     Sieben
    -0.28
    Referensi
    -0.28
    Билгалдахарш
    -0.28
    POSITIVE LOGITS
    PerformLayout
    0.74
     مشين
    0.60
    transQ
    0.59
    <pad>
    0.57
    <unused42>
    0.57
    <unused68>
    0.57
    <unused52>
    0.57
    <unused16>
    0.56
    <unused8>
    0.56
    [@BOS@]
    0.56
    Act Density 0.029%

    No Known Activations