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

    Neuronpedia

    INDEX
    Explanations

    programming and code-related structures or definitions

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

    Section identifiers with brackets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ſammen
    -0.77
     queſto
    -0.73
    <unused16>
    -0.73
    <unused8>
    -0.73
    <unused52>
    -0.73
    <unused23>
    -0.73
    [@BOS@]
    -0.73
    <unused41>
    -0.73
    <unused28>
    -0.73
    <unused3>
    -0.73
    POSITIVE LOGITS
     AssemblyProduct
    0.38
    帖最后由
    0.37
    >{@
    0.33
    WEBPACK
    0.33
    AccessorTable
    0.30
    findpost
    0.29
    <h1>
    0.29
    Distribuzione
    0.28
     the
    0.27
     незавершена
    0.27
    Act Density 0.185%

    No Known Activations