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

    Neuronpedia

    INDEX
    Explanations

    commercial version of ORACLE

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     வேத
    0.43
    راء
    0.41
     rejoicing
    0.40
     शहर
    0.39
    Глав
    0.39
    /');
    0.37
    າ
    0.37
     hugged
    0.37
     groaned
    0.37
    ന്‍സ്
    0.37
    POSITIVE LOGITS
    Quartz
    0.42
    fix
    0.40
    Bun
    0.39
    Ping
    0.38
     System
    0.38
     Note
    0.38
     DATABASE
    0.38
     цю
    0.38
    Fix
    0.38
    ключа
    0.37
    Act Density 0.002%

    No Known Activations