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

    Neuronpedia

    INDEX
    Explanations

    programming-related terms, specifically data types and operations associated with memory access

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

    byte sizes and counts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     InputDecoration
    -0.51
     &___
    -0.50
    LookAnd
    -0.48
    StateToProps
    -0.44
    wapV
    -0.43
    DotNetBar
    -0.40
     ThemeData
    -0.40
     Witkin
    -0.40
    bkz
    -0.39
    ScreenState
    -0.37
    POSITIVE LOGITS
     ErrIntOverflow
    0.42
     ब्रेकडाउन
    0.40
    zee
    0.40
    emples
    0.38
     Ohren
    0.37
    Datuak
    0.37
    oar
    0.37
     guessed
    0.36
     instant
    0.36
    Aholisi
    0.36
    Act Density 0.043%

    No Known Activations