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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     twice
    -0.07
     security
    -0.06
     Customers
    -0.06
     easiest
    -0.06
    냥
    -0.06
    _SYNC
    -0.06
    -nine
    -0.06
     له
    -0.06
     caches
    -0.06
     second
    -0.06
    POSITIVE LOGITS
    ยนตร
    0.08
    真是
    0.07
     Stephanie
    0.07
     TouchableOpacity
    0.07
     impart
    0.07
    .cam
    0.06
    ,—
    0.06
     ◎
    0.06
     Ngân
    0.06
    าตร
    0.06
    Act Density 0.228%

    No Known Activations