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

    Neuronpedia

    INDEX
    Explanations

    terms related to logic programming and computational techniques

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

    describing techniques and concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    aarrggbb
    -0.55
     '\\;'
    -0.47
    penup
    -0.43
    @[+][
    -0.40
    ensement
    -0.38
     ✭✭
    -0.38
    RegressionTest
    -0.37
     vPvB
    -0.37
    Chham
    -0.37
    BufferException
    -0.36
    POSITIVE LOGITS
    IsMutable
    0.46
     rozwiąz
    0.43
     spoluprá
    0.42
    CppCodeGen
    0.41
    为自己
    0.40
    ⓧ
    0.39
    errHandler
    0.39
    orologio
    0.39
    mpo
    0.38
     compatibility
    0.37
    Act Density 0.280%

    No Known Activations