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

    Neuronpedia

    INDEX
    Explanations

    sudden stops or movements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     iyong
    0.44
    ৳
    0.43
     doigt
    0.42
     eller
    0.39
     ooit
    0.38
     your
    0.37
     وحتى
    0.37
    손
    0.37
    值得
    0.37
    逛
    0.37
    POSITIVE LOGITS
     उसने
    0.46
     repeated
    0.44
     оказалось
    0.43
     contradicted
    0.41
     collided
    0.39
     realizaron
    0.39
     retrospect
    0.39
     Appellant
    0.39
     unloaded
    0.39
     destabil
    0.38
    Act Density 0.001%

    No Known Activations