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

    Neuronpedia

    INDEX
    Explanations

    individually

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     scope
    -0.06
    References
    -0.06
     cooled
    -0.06
    μάτων
    -0.06
     supplemented
    -0.06
    者的
    -0.06
     багатьох
    -0.06
     broader
    -0.06
     role
    -0.06
    電影
    -0.06
    POSITIVE LOGITS
    .XPath
    0.07
    {lng
    0.07
    _waiting
    0.07
     Telegraph
    0.06
     mand
    0.06
    斗
    0.06
    .constant
    0.06
    _const
    0.06
     pprint
    0.06
    _strike
    0.06
    Act Density 0.002%

    No Known Activations