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

    Neuronpedia

    INDEX
    Explanations

    plotting functions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    શન
    0.43
    Nell
    0.41
     ಸ್ಥಳ
    0.40
    โย
    0.40
     হইলেই
    0.40
    ｿ
    0.40
    मिटेड
    0.39
    ᷅
    0.39
    IsMethod
    0.39
    ntz
    0.39
    POSITIVE LOGITS
     Früh
    0.40
     reaf
    0.39
     Janus
    0.37
      
    0.37
    ளான
    0.36
     frag
    0.35
     მკ
    0.35
    =(\
    0.35
     ил
    0.35
     rupt
    0.35
    Act Density 0.000%

    No Known Activations