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

    Neuronpedia

    INDEX
    Explanations

    terms related to serialization and data structure management in programming

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

    Java object serialization

    np_acts-logits-general · gemini-2.0-flash

    serialization and preservation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Bethlehem
    -0.46
     BorderRadius
    -0.45
     Pythagoras
    -0.43
    GEBURTS
    -0.43
     useStyles
    -0.43
    QueryBuilder
    -0.42
     scissor
    -0.42
     RID
    -0.42
     שוליים
    -0.41
    lą
    -0.41
    POSITIVE LOGITS
     freeze
    1.29
     preservation
    1.15
     frozen
    1.15
     Freeze
    1.13
     Preservation
    1.09
    freeze
    1.07
     freezes
    1.06
     preserved
    1.05
     freezed
    1.04
     froze
    1.03
    Act Density 0.404%

    No Known Activations