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

    Neuronpedia

    INDEX
    Explanations

    performance benchmarks and scores

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     experimenting
    0.41
     Maldonado
    0.41
     experimentation
    0.40
     speriment
    0.39
     experiment
    0.38
     కుమార్
    0.38
    ลิ
    0.38
     Eve
    0.38
     experimented
    0.38
    판
    0.38
    POSITIVE LOGITS
     benchmark
    0.56
     benchmarks
    0.56
     measurement
    0.54
    networking
    0.49
     measurements
    0.48
    Benchmark
    0.48
    score
    0.47
    bench
    0.47
     score
    0.46
     models
    0.46
    Act Density 0.025%

    No Known Activations