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

    Neuronpedia

    INDEX
    Explanations

    C# Linq usage

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    嚯
    0.76
     عملکرد
    0.73
    GoString
    0.73
     blant
    0.71
    崤
    0.71
     Cardano
    0.71
     Bit
    0.70
     Machu
    0.70
    সম
    0.69
    ĕç
    0.69
    POSITIVE LOGITS
     Rhine
    0.77
     aynı
    0.75
    धीर
    0.73
     giud
    0.69
     saya
    0.69
     mercy
    0.68
     auth
    0.68
     jk
    0.68
     juez
    0.67
     ਕਰ
    0.67
    Act Density 0.007%

    No Known Activations