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

    Neuronpedia

    INDEX
    Explanations

    programming-related constructs such as functions and data types

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

    Non-English programming or log data

    np_acts-logits-general · gemini-2.0-flash

    CUDA, C++ code snippets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    prefixer
    -0.60
    ้ง
    -0.59
     continúas
    -0.59
    InteropServices
    -0.55
     Haring
    -0.55
    icionar
    -0.54
     HttpNotFound
    -0.53
    ToMany
    -0.49
    UniformLocation
    -0.49
     ReactDOM
    -0.49
    POSITIVE LOGITS
    ьаж
    0.72
    ########.
    0.66
    kháu
    0.54
     članak
    0.54
     orar
    0.53
    ?')
    0.53
     CURIAM
    0.52
    zija
    0.52
    CreateModel
    0.52
     accepté
    0.52
    Act Density 0.054%

    No Known Activations