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

    Neuronpedia

    INDEX
    Explanations

    sql, python, regex scripts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Data
    0.72
    Data
    0.65
     데이터
    0.63
     Database
    0.62
     named
    0.60
     data
    0.60
     everything
    0.59
     Daten
    0.59
     database
    0.59
     Everything
    0.58
    POSITIVE LOGITS
    script
    0.82
    jsdel
    0.77
     script
    0.74
     scripting
    0.72
    vorsch
    0.72
    Script
    0.71
     keç
    0.70
    promises
    0.68
     scripts
    0.68
     स्क्रिप्ट
    0.68
    Act Density 0.169%

    No Known Activations