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

    Neuronpedia

    INDEX
    Explanations

    titles of creative works such as movies, books and TV shows

    oai_token-act-pair · gemini-2.0-flash

    The

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     isNameExpr
    -0.55
     TPS
    -0.48
     CURIAM
    -0.48
    queryInterface
    -0.48
     ◆
    -0.47
    InstanceState
    -0.47
    yntaxException
    -0.45
     gradova
    -0.45
    couvrez
    -0.45
    zbęd
    -0.45
    POSITIVE LOGITS
    Geplaatst
    0.69
     Conquer
    0.56
     Spell
    0.56
    GHIJKLM
    0.56
     Beasts
    0.54
     Wicked
    0.53
     Exile
    0.53
     Bandit
    0.53
    AMENTE
    0.52
     Tempt
    0.52
    Act Density 2.575%

    No Known Activations