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

    Neuronpedia

    INDEX
    Explanations

    measuring and detecting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ketentuan
    0.85
    スペシャル
    0.81
    WebHost
    0.81
    riters
    0.80
    mux
    0.79
     Writers
    0.79
     پست
    0.76
    ALTERN
    0.76
     прошу
    0.75
    iapkan
    0.75
    POSITIVE LOGITS
     detecting
    2.05
     quantifying
    1.92
     detects
    1.91
     accurately
    1.85
     accurate
    1.84
     detect
    1.84
     monitoring
    1.76
     detection
    1.74
     측정
    1.73
     measuring
    1.72
    Act Density 0.928%

    No Known Activations