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

    Neuronpedia

    INDEX
    Explanations

    lists followed by descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     või
    1.21
     или
    1.14
     किंवा
    1.13
     vagy
    1.13
     veya
    1.09
     لاءِ
    1.05
     ወይም
    1.01
     atau
    0.98
    nije
    0.95
     או
    0.95
    POSITIVE LOGITS
     சுமார்
    0.98
     ebenfalls
    0.94
     They
    0.88
     remnants
    0.86
    ↵
    0.85
     two
    0.85
    Organizer
    0.84
     Sunrise
    0.83
    ↵↵
    0.83
     उन्होंने
    0.82
    Act Density 0.086%

    No Known Activations