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

    Neuronpedia

    INDEX
    Explanations

    playful subversion or charm

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    得意
    0.48
    findViewById
    0.46
    貿
    0.43
     असलेला
    0.42
    كمل
    0.42
    ডিং
    0.42
     hepatocytes
    0.42
    編集
    0.42
     AppBsky
    0.42
    äsident
    0.41
    POSITIVE LOGITS
     tamb
    0.40
     aw
    0.40
     eyebrows
    0.39
     blast
    0.39
     gé
    0.39
     cynicism
    0.37
     liquef
    0.37
     Tamb
    0.36
     argument
    0.36
     loot
    0.36
    Act Density 0.000%

    No Known Activations