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

    Neuronpedia

    INDEX
    Explanations

    programming-related terms and structures

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

    class, circuit, object

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    GEBURTSDATUM
    -0.93
    +#+
    -0.88
    #+#
    -0.85
    elemField
    -0.80
     utafitiHapana
    -0.79
    +#+#
    -0.75
    UserScript
    -0.75
    ########.
    -0.75
    transQ
    -0.74
     OMITBAD
    -0.74
    POSITIVE LOGITS
     stand
    0.40
    ara
    0.35
    EClass
    0.34
    .
    0.32
     similarly
    0.32
     Stand
    0.31
    class
    0.30
    ,
    0.30
    rat
    0.30
     similar
    0.30
    Act Density 0.017%

    No Known Activations