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

    Neuronpedia

    INDEX
    Explanations

    working

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     TO
    -0.07
    ULD
    -0.06
    506
    -0.06
    沢
    -0.06
     Clyde
    -0.06
    :NSLocalizedString
    -0.06
     Č
    -0.06
     المد
    -0.06
     tenga
    -0.06
    桐
    -0.06
    POSITIVE LOGITS
     working
    0.07
     hurried
    0.07
    ]))
    0.07
     learning
    0.07
     Twin
    0.07
     record
    0.07
     returning
    0.07
     recurring
    0.07
     hurt
    0.06
    ()))
    0.06
    Act Density 0.026%

    No Known Activations