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

    Neuronpedia

    INDEX
    Explanations

    formatted text elements, particularly bold and emphasized text

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

    HTML bold tags

    np_acts-logits-general · gemini-2.0-flash

    interface elements or settings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    -
    -0.35
     assist
    -0.33
    AnimationsModule
    -0.33
     and
    -0.33
    쿵
    -0.31
     asistencia
    -0.31
    е
    -0.30
    LElement
    -0.30
    had
    -0.30
     +
    -0.29
    POSITIVE LOGITS
    <unused80>
    0.79
    <unused52>
    0.79
    <unused41>
    0.79
    <unused51>
    0.79
    <unused14>
    0.79
    <unused8>
    0.79
    <unused17>
    0.79
    <unused23>
    0.79
    [@BOS@]
    0.79
    <unused3>
    0.79
    Act Density 0.470%

    No Known Activations