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

    Neuronpedia

    INDEX
    Explanations

    software library paths

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    谔
    0.49
    нинград
    0.45
    ড়ন
    0.45
    तोंडा
    0.43
    鹑
    0.40
     Schlüssel
    0.40
     lever
    0.39
    諰
    0.39
     പട്ട
    0.39
     गन्ना
    0.39
    POSITIVE LOGITS
     library
    0.73
    library
    0.70
    jar
    0.67
    lib
    0.66
     jar
    0.63
     libraries
    0.63
     JAR
    0.63
     lib
    0.61
    Library
    0.61
     LIBRARY
    0.61
    Act Density 0.002%

    No Known Activations