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

    Neuronpedia

    INDEX
    Explanations

    proper nouns, particularly names and specific references

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

    people and technical terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    GEBURTSDATUM
    -0.68
    InjectAttribute
    -0.62
     NSCoder
    -0.54
    badlogic
    -0.52
    StoryboardSegue
    -0.51
    ")));
    -0.48
    hubanes
    -0.46
    afficheront
    -0.46
    Autoritní
    -0.45
    XtraGrid
    -0.44
    POSITIVE LOGITS
     alpaca
    0.65
    rsiniz
    0.60
     Pompeo
    0.59
    Sockets
    0.57
     Hathaway
    0.55
     Lovato
    0.54
    fillColor
    0.54
     SOCK
    0.53
    unknownFields
    0.53
    PROTOBUF
    0.52
    Act Density 0.005%

    No Known Activations