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

    Neuronpedia

    INDEX
    Explanations

    instead of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     kesk
    -0.94
    sorption
    -0.85
    外部連結
    -0.84
    rillo
    -0.84
    feather
    -0.82
    ichtlich
    -0.82
    ир
    -0.82
     sichern
    -0.82
     weiteren
    -0.81
     νέ
    -0.81
    POSITIVE LOGITS
     instead
    1.27
     Instead
    0.94
    Instead
    0.89
    instead
    0.87
     CPA
    0.79
     вместо
    0.78
     justru
    0.74
     geniş
    0.70
    แทน
    0.69
     فوق
    0.69
    Act Density 0.008%

    No Known Activations