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

    Neuronpedia

    INDEX
    Explanations

    humanitarian or ceasefire pauses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     probably
    0.45
     uner
    0.45
     prawdopod
    0.43
     aldı
    0.40
     miesią
    0.40
     uncoated
    0.40
     pairs
    0.39
     months
    0.39
    nies
    0.39
     jaws
    0.38
    POSITIVE LOGITS
     মানবতার
    0.47
     humanitarian
    0.47
     Humanitarian
    0.44
     आवाहन
    0.42
     不要
    0.42
     ceasefire
    0.41
     Không
    0.41
     मानवता
    0.40
     শান্তিপূর্ণ
    0.40
    しましょう
    0.39
    Act Density 0.001%

    No Known Activations