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

    Neuronpedia

    INDEX
    Explanations

    Japanese expressions and musical notations

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

    repeated words and punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     المعيارى
    -1.16
    <unused3>
    -1.04
    <unused16>
    -1.04
    <unused42>
    -1.04
    <unused43>
    -1.04
    [@BOS@]
    -1.04
    <unused8>
    -1.04
    <unused41>
    -1.04
    <unused51>
    -1.04
    <unused28>
    -1.04
    POSITIVE LOGITS
    ↵↵
    0.35
     
    0.31
    ↵
    0.30
    <eos>
    0.27
    .
    0.27
    ↵↵↵
    0.25
    Collections
    0.25
    .,
    0.25
    。
    0.25
    !
    0.23
    Act Density 0.033%

    No Known Activations