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

    Neuronpedia

    INDEX
    Explanations

    snd

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    =z
    -0.07
     pueden
    -0.07
    =P
    -0.07
    entication
    -0.07
    __
    -0.07
    =m
    -0.06
    absolute
    -0.06
    ])*
    -0.06
    "She
    -0.06
     Peyton
    -0.06
    POSITIVE LOGITS
    輕
    0.07
    Encode
    0.07
    ply
    0.06
    ån
    0.06
     (_,
    0.06
     RDD
    0.06
    SequentialGroup
    0.06
    温度
    0.06
    擊
    0.06
    наче
    0.06
    Act Density 0.003%

    No Known Activations