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

    Neuronpedia

    INDEX
    Explanations

    sexual harassment and firearms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    இந்த
    0.41
     theses
    0.39
     এই
    0.38
     THESE
    0.38
    these
    0.38
     obecnie
    0.38
     vilka
    0.37
    Diese
    0.37
     these
    0.36
    braith
    0.36
    POSITIVE LOGITS
     And
    0.46
     പക്ഷേ
    0.46
     এমনকি
    0.45
     Bahkan
    0.44
     nawet
    0.42
     даже
    0.41
     bahkan
    0.41
     Даже
    0.40
     zelfs
    0.40
    媲
    0.38
    Act Density 0.000%

    No Known Activations