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

    Neuronpedia

    INDEX
    Explanations

    independent clauses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     constaté
    0.44
    झ्
    0.44
    徠
    0.42
    وم
    0.41
    ocoder
    0.41
     vendu
    0.41
    ਟੀ
    0.41
     grail
    0.41
    ार्ट
    0.41
    ்டர்
    0.41
    POSITIVE LOGITS
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.44
     endeavour
    0.43
     pitan
    0.43
     misty
    0.43
    ល្អ
    0.42
     pavattati
    0.42
     cryptic
    0.41
     imassa
    0.41
    ິ່ງ
    0.41
     heighten
    0.41
    Act Density 0.003%

    No Known Activations