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

    Neuronpedia

    INDEX
    Explanations

    references to programming concepts or code structures

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

    parentheses and single letters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     BorderSide
    -0.85
    <unused68>
    -0.82
    CppMethod
    -0.82
    <pad>
    -0.82
    <unused41>
    -0.82
    <unused16>
    -0.82
    <unused23>
    -0.82
    <unused14>
    -0.82
    [@BOS@]
    -0.82
    <unused8>
    -0.82
    POSITIVE LOGITS
    Espèce
    0.30
    <eos>
    0.25
    Common
    0.25
     hopefully
    0.24
     potret
    0.24
    澡
    0.23
     common
    0.23
    latest
    0.22
     tuviera
    0.22
    ↵↵
    0.21
    Act Density 0.017%

    No Known Activations