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

    Neuronpedia

    INDEX
    Explanations

    .NET Framework methods

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    favor
    -0.08
     Outstanding
    -0.08
    _ED
    -0.07
     SY
    -0.07
    Connected
    -0.07
    OLUME
    -0.07
    .Summary
    -0.07
     kilomet
    -0.07
    实体经济
    -0.07
     tí
    -0.07
    POSITIVE LOGITS
    要做好
    0.07
    ある程度
    0.07
    ";↵↵
    0.07
    _div
    0.07
     kötü
    0.07
    sizes
    0.07
     hunted
    0.07
    针对
    0.06
    可以让
    0.06
    >';↵
    0.06
    Act Density 0.001%

    No Known Activations