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

    Neuronpedia

    INDEX
    Explanations

    consequences and aftermath

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     congru
    0.45
     واضح
    0.44
     наличии
    0.44
     అన్ని
    0.44
     चांगले
    0.43
     synerg
    0.43
     কালিক
    0.43
     BufferedWriter
    0.42
     स्पष्ट
    0.42
     Undergraduate
    0.42
    POSITIVE LOGITS
     afterwards
    0.59
     afterward
    0.54
     aftermath
    0.52
    resulting
    0.49
     devait
    0.49
     musste
    0.48
     придется
    0.47
    repair
    0.47
     moest
    0.45
     mussten
    0.45
    Act Density 0.003%

    No Known Activations