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

    Neuronpedia

    INDEX
    Explanations

    references to data storage types and byte-related concepts

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

    byte fields

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ScopeManager
    -0.48
     незавершена
    -0.42
     Infórmanos
    -0.40
     widerrufen
    -0.40
    MLLoader
    -0.40
     సౌకర్య
    -0.39
    inher
    -0.38
    Становништво
    -0.36
     Grunde
    -0.36
     Lucerne
    -0.36
    POSITIVE LOGITS
    Bytes
    2.77
     Bytes
    1.88
    BYTES
    1.25
    getBytes
    1.18
    GetBytes
    1.01
    Byte
    0.90
    bytes
    0.88
     bytes
    0.87
     Byte
    0.85
     byte
    0.69
    Act Density 0.005%

    No Known Activations