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

    Neuronpedia

    INDEX
    Explanations

    :

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     reload
    -0.07
     diagonal
    -0.07
    capital
    -0.06
     heater
    -0.06
     Hình
    -0.06
     Grave
    -0.06
     deaf
    -0.06
    _safe
    -0.06
     finding
    -0.06
     billing
    -0.06
    POSITIVE LOGITS
    ωμάτιο
    0.07
     카지노
    0.07
     تاريخ
    0.07
     Cambodia
    0.06
     calm
    0.06
     Honolulu
    0.06
    ，可
    0.06
     требует
    0.06
     Plantae
    0.06
     thoại
    0.06
    Act Density 0.114%

    No Known Activations