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

    Neuronpedia

    INDEX
    Explanations

    instances of structured data or code-related elements

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

    codes or syntax elements related to programming or data structures

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

    parenthesized letters or numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    CloseOperation
    -0.74
    SBATCH
    -0.68
    󠁢
    -0.63
    rungsseite
    -0.62
     Roskov
    -0.61
     betweenstory
    -0.56
    GEBURTSDATUM
    -0.55
    .*")]
    -0.55
    ViewFeatures
    -0.54
     insuffisamment
    -0.53
    POSITIVE LOGITS
     E
    0.93
    E
    0.69
    getE
    0.63
     Э
    0.63
     ET
    0.59
     É
    0.58
     ES
    0.57
     ई
    0.56
     EE
    0.56
    Ｅ
    0.56
    Act Density 0.085%

    No Known Activations