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

    Neuronpedia

    INDEX
    Explanations

    bruised plum

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    unication
    0.39
     गुंतवणूक
    0.39
    ்க்கு
    0.38
     Seat
    0.37
    窜
    0.37
    allel
    0.37
    釟
    0.37
     इक्वेशन
    0.36
     పొంద
    0.36
     محاسبه
    0.35
    POSITIVE LOGITS
     masti
    0.36
     Влади
    0.36
     coke
    0.35
     mildly
    0.35
     qua
    0.34
     buttermilk
    0.34
     com
    0.34
    ্যান্ড
    0.34
     blacks
    0.34
    tipped
    0.34
    Act Density 0.000%

    No Known Activations