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

    Neuronpedia

    INDEX
    Explanations

    sort and filter

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ہ
    1.23
    тился
    1.05
     приобрета
    1.05
     choisi
    1.03
    هُ
    1.02
    하였
    1.02
    𝗶
    1.02
    1.02
     Freude
    1.01
     Chakraborty
    1.01
    POSITIVE LOGITS
     harassing
    0.93
     takes
    0.88
    takes
    0.88
     breaks
    0.87
     suffers
    0.87
     Unusual
    0.86
     hasn
    0.84
     hates
    0.84
     pulls
    0.83
     Policing
    0.83
    Act Density 0.000%

    No Known Activations