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

    Neuronpedia

    INDEX
    Explanations

    white spaces or gaps in text

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

    mathematical problems and suppositions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    principalTable
    -0.52
     pungkasnya
    -0.42
     ویکی‌آمباردا
    -0.40
    GeoNames
    -0.40
    flashdata
    -0.39
    WebElementEntity
    -0.39
    setVerticalGroup
    -0.38
    guenos
    -0.38
     Pristupljeno
    -0.38
     Roskov
    -0.37
    POSITIVE LOGITS
     zwiſchen
    0.68
     dieſes
    0.67
    <unused17>
    0.67
    <unused14>
    0.66
    <unused68>
    0.66
    [@BOS@]
    0.66
    <unused28>
    0.66
    <unused51>
    0.66
    <unused3>
    0.66
    <unused8>
    0.66
    Act Density 0.060%

    No Known Activations