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

    Neuronpedia

    INDEX
    Explanations

    references to threading or concurrency concepts

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

    Code, math, or foreign language fragments

    np_acts-logits-general · gemini-2.0-flash

    *, i, math followed by numbers or specific words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    reads
    -0.54
    WriteAttribute
    -0.53
     רח
    -0.48
     Codable
    -0.48
    NOPE
    -0.48
    ########.
    -0.48
    Heinz
    -0.48
    Reads
    -0.47
    enerys
    -0.47
    pantalones
    -0.47
    POSITIVE LOGITS
     InputDecoration
    0.59
    Portály
    0.56
    qtype
    0.54
    ьаж
    0.53
    GraphicsUnit
    0.52
    انيف
    0.52
    AutoresizingMask
    0.52
     pinulongan
    0.52
     iconFacebook
    0.52
     solteiro
    0.51
    Act Density 0.018%

    No Known Activations