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

    Neuronpedia

    INDEX
    Explanations

    concepts related to development and impact in research contexts

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

    describing results and capabilities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    RenderAtEndOf
    -0.58
     hence
    -0.57
    Personensuche
    -0.53
    ipients
    -0.51
     sobretudo
    -0.51
     thrice
    -0.50
     hitherto
    -0.50
     acaso
    -0.49
    Czytaj
    -0.49
     chi̍t
    -0.48
    POSITIVE LOGITS
    IntoConstraints
    0.48
    umumkan
    0.42
     kou
    0.40
    DataBase
    0.40
    setCharacter
    0.40
     frightened
    0.40
     creepy
    0.39
     confused
    0.39
    stretchr
    0.39
    Decoration
    0.39
    Act Density 0.444%

    No Known Activations