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

    Neuronpedia

    INDEX
    Explanations

    recently/lately

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     teaspoon
    -0.06
     complications
    -0.06
    ATIONS
    -0.06
    _executor
    -0.05
     Quaternion
    -0.05
    -upper
    -0.05
     questionable
    -0.05
    Calculator
    -0.05
    ्तम
    -0.05
    Desk
    -0.05
    POSITIVE LOGITS
    arrison
    0.08
    attering
    0.07
     Reporter
    0.07
    uffle
    0.07
     assured
    0.06
     entropy
    0.06
     ar
    0.06
     pitched
    0.06
    من
    0.06
    _business
    0.06
    Act Density 0.029%

    No Known Activations