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

    Neuronpedia

    INDEX
    Explanations

    view

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     تستخدم
    -0.09
     destinations
    -0.08
     popul
    -0.08
     volumes
    -0.08
     temperature
    -0.07
     recreational
    -0.07
     تعتمد
    -0.07
     modular
    -0.07
    imed
    -0.07
    (bytes
    -0.07
    POSITIVE LOGITS
    朝
    0.09
     clad
    0.09
    覆
    0.09
     depiction
    0.08
     обз
    0.08
    窗
    0.08
     모습을
    0.08
     모습
    0.08
    排列
    0.08
     testemun
    0.08
    Act Density 0.005%

    No Known Activations