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

    Neuronpedia

    INDEX
    Explanations

    "ised", "ized"

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    滿
    -0.08
     neces
    -0.08
     investigative
    -0.08
     mê
    -0.08
     女
    -0.07
     spectacle
    -0.07
     لازم
    -0.07
     mää
    -0.07
     Mapping
    -0.07
     Iris
    -0.07
    POSITIVE LOGITS
     предотвращ
    0.10
    避免
    0.10
     avoids
    0.10
     избег
    0.10
     prevents
    0.09
     وعدم
    0.09
     éviter
    0.09
     સુર
    0.09
     evitar
    0.09
     prohibits
    0.09
    Act Density 0.002%

    No Known Activations