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

    Neuronpedia

    INDEX
    Explanations

    punctuation and specific phrases indicating actions or interactions

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

    Text after commas

    np_acts-logits-general · gemini-2.0-flash

    words following lists

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     useParams
    -0.32
    </em>
    -0.31
    ↵↵
    -0.29
     einzu
    -0.29
     lleg
    -0.29
     in
    -0.28
    ↵
    -0.28
    Zus
    -0.27
     ek
    -0.27
     "
    -0.27
    POSITIVE LOGITS
    ſſung
    0.84
    ſelf
    0.82
    <unused16>
    0.81
    [@BOS@]
    0.81
    <unused8>
    0.81
    <unused43>
    0.81
    <unused80>
    0.81
    <unused41>
    0.81
    <unused3>
    0.81
    <unused23>
    0.81
    Act Density 0.389%

    No Known Activations