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

    Neuronpedia

    INDEX
    Explanations

    MLB

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     mask
    -0.08
    .methods
    -0.08
    用
    -0.07
    ielding
    -0.07
    浦
    -0.07
    对着
    -0.07
    -node
    -0.07
    _mgmt
    -0.07
    锁定
    -0.07
     Tiger
    -0.07
    POSITIVE LOGITS
    工商联
    0.08
    :UIAlert
    0.07
     agreed
    0.07
    东京
    0.07
     Contrib
    0.07
    小编一起
    0.07
    yı
    0.07
     the
    0.07
     prominently
    0.07
    经开
    0.07
    Act Density 0.001%

    No Known Activations