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

    Neuronpedia

    INDEX
    Explanations

    names of notable individuals

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

    person names followed by last name

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    <unused8>
    -0.89
    [@BOS@]
    -0.89
    <unused41>
    -0.89
    <unused80>
    -0.89
    <unused43>
    -0.89
    <unused52>
    -0.88
    <unused74>
    -0.88
    <unused51>
    -0.88
    <unused14>
    -0.88
    <unused28>
    -0.88
    POSITIVE LOGITS
    .
    0.50
    %.
    0.30
    CDCl
    0.28
    ™.
    0.27
    *.
    0.27
    。
    0.26
     .
    0.25
    ".
    0.25
    ."
    0.24
    ².
    0.24
    Act Density 0.064%

    No Known Activations