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

    Neuronpedia

    INDEX
    Explanations

    keywords related to data structures and protocols, particularly those defining repeated and optional fields in message formats

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

    Protobuf repeated optional Sint fields

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     salido
    -0.38
     Jurí
    -0.38
    hausen
    -0.37
     Sociale
    -0.36
    zub
    -0.35
     sucedido
    -0.35
     Sociales
    -0.35
    pisah
    -0.35
    Mapper
    -0.34
    出了
    -0.34
    POSITIVE LOGITS
     defaultstate
    0.74
     <<<<<<<<<<<<<<
    0.73
     Савезне
    0.72
     Италијани
    0.72
    хьтан
    0.69
    SequentialGroup
    0.67
     ब्रेकडाउन
    0.66
    tvguidetime
    0.65
     незавершена
    0.64
     Protobuf
    0.64
    Act Density 0.007%

    No Known Activations