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

    Neuronpedia

    INDEX
    Explanations

    block delimiters and structural elements in code

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

    programmatic structures and types

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ➌
    -0.52
    IntoConstraints
    -0.44
     pouvoit
    -0.40
    voo
    -0.40
    ==",
    -0.39
    culable
    -0.38
    󠁢
    -0.38
    olesome
    -0.38
    ﷻ
    -0.37
     étoit
    -0.37
    POSITIVE LOGITS
     disambiguazione
    0.68
     autorytatywna
    0.61
    GTCX
    0.50
    astéroïdes
    0.45
    verwijspagina
    0.44
    SBATCH
    0.43
     Normdatei
    0.42
    GEBURTSDATUM
    0.42
    saraba
    0.41
     PyTuple
    0.40
    Act Density 0.064%

    No Known Activations