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

    Neuronpedia

    INDEX
    Explanations

    UTF-8 encoding

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     carinatis
    0.54
     sécrétion
    0.53
     تړل
    0.51
     行っ
    0.51
     pavattati
    0.49
     صہیونیوں
    0.49
    apayati
    0.49
     وګټ
    0.49
    }^{+}+\
    0.48
     ننوت
    0.48
    POSITIVE LOGITS
    E
    0.54
     at
    0.52
     off
    0.52
     Remote
    0.52
      
    0.50
    and
    0.50
    0.49
    o
    0.48
     a
    0.48
     other
    0.48
    Act Density 0.000%

    No Known Activations