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

    Neuronpedia

    INDEX
    Explanations

    official capacity

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     stewardship
    -0.88
    好み
    -0.77
    uninstall
    -0.77
    maid
    -0.72
    Occupation
    -0.71
    jsonString
    -0.71
    ivory
    -0.70
     lợi
    -0.70
     ApJ
    -0.69
     prosecution
    -0.69
    POSITIVE LOGITS
     constitutional
    1.19
     Constitutional
    0.90
     Pera
    0.87
     municipality
    0.85
     deprivation
    0.84
    をクリック
    0.84
     constitution
    0.83
     PLN
    0.83
     Bauch
    0.81
     officials
    0.79
    Act Density 0.089%

    No Known Activations