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

    Neuronpedia

    INDEX
    Explanations

    the same

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     vẫn
    0.49
     vials
    0.46
     Boltzmann
    0.44
     Joss
    0.44
     crystallized
    0.44
    žev
    0.43
     vodka
    0.42
     breaths
    0.42
     scarlet
    0.42
    rát
    0.40
    POSITIVE LOGITS
    ныгы
    0.46
     کنیم
    0.41
    ण्यासाठी
    0.40
     書い
    0.40
     বাহুল্য
    0.40
     العالمين
    0.39
    ERCISE
    0.39
    💏
    0.39
    ക്കുന്ന
    0.39
     hermosa
    0.39
    Act Density 0.005%

    No Known Activations