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

    Neuronpedia

    INDEX
    Explanations

    elements of programming syntax related to protocol buffers and data structure definitions

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

    Protobuf-related code

    np_acts-logits-general · gemini-2.0-flash

    proto: types and standard declarations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Taktlose
    -0.50
    تقاوى
    -0.50
     autorytatywna
    -0.47
    fillType
    -0.46
     دیکھیے
    -0.46
     Normdatei
    -0.46
    writeField
    -0.45
    Personendaten
    -0.44
    TagMode
    -0.44
    AndEndTag
    -0.43
    POSITIVE LOGITS
     pluie
    0.42
    Doktor
    0.40
     ASSIST
    0.39
    Rescue
    0.39
     Doctrine
    0.39
    whites
    0.39
    吃到
    0.39
    verme
    0.39
    Tasting
    0.39
    toire
    0.38
    Act Density 0.193%

    No Known Activations