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

    Neuronpedia

    INDEX
    Explanations

    force and slowing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     marquées
    0.38
     সেগুলি
    0.38
    Psych
    0.37
    imageData
    0.37
     የታ
    0.37
     ውሃ
    0.37
     имму
    0.36
    retrato
    0.36
    करण
    0.36
     હવા
    0.36
    POSITIVE LOGITS
     poppy
    0.44
     bach
    0.41
     topic
    0.40
     hanem
    0.40
     topik
    0.39
     Parks
    0.39
    もちろん
    0.39
     parks
    0.38
    annan
    0.38
     complicating
    0.38
    Act Density 0.001%

    No Known Activations