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

    Neuronpedia

    INDEX
    Explanations

    comma

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     cert
    -0.07
     امام
    -0.07
    snap
    -0.06
    (signature
    -0.06
    重
    -0.06
     OLD
    -0.06
    -de
    -0.06
     Asian
    -0.06
     티
    -0.06
    722
    -0.06
    POSITIVE LOGITS
    ìm
    0.06
    ộn
    0.06
     khoản
    0.06
    \Request
    0.06
    card
    0.06
     nan
    0.06
     laundry
    0.06
    geometry
    0.05
     africa
    0.05
    یری
    0.05
    Act Density 0.003%

    No Known Activations