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

    Neuronpedia

    INDEX
    Explanations

    metrics, ratios, rates, yield, GDP

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     neuen
    0.73
    Password
    0.73
     പുതിയ
    0.72
    新しい
    0.69
     neues
    0.69
     weiteres
    0.68
    Creating
    0.68
    Prepare
    0.68
    全新的
    0.67
     neue
    0.66
    POSITIVE LOGITS
     ratio
    1.14
     ratios
    1.05
     coefficient
    1.02
     coefficients
    1.01
     rates
    0.98
     percentage
    0.97
     rate
    0.96
     pourcentage
    0.95
     capacity
    0.94
     metrics
    0.93
    Act Density 0.046%

    No Known Activations