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

    Neuronpedia

    INDEX
    Explanations

    emphasis on quality and variation in content

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

    qualifier before noun

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Personendaten
    -1.16
    ロウィン
    -1.08
    <unused41>
    -0.96
    <unused51>
    -0.96
    <unused16>
    -0.96
    [@BOS@]
    -0.96
    <unused14>
    -0.95
    <unused28>
    -0.95
    <unused8>
    -0.95
    <unused3>
    -0.95
    POSITIVE LOGITS
    .
    0.63
    ;
    0.37
    :
    0.33
    <eos>
    0.28
    ...
    0.28
    ..
    0.27
    1
    0.26
    ↵↵
    0.25
    ."
    0.24
    .,
    0.24
    Act Density 0.136%

    No Known Activations