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

    Neuronpedia

    INDEX
    Explanations

    authorize

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     memnun
    -0.07
    観
    -0.07
    Priority
    -0.07
     fclose
    -0.07
     falling
    -0.07
    mai
    -0.06
    思考
    -0.06
    胶
    -0.06
    flies
    -0.06
    效果
    -0.06
    POSITIVE LOGITS
     authorized
    0.10
     authorised
    0.09
     Authorized
    0.07
     authorization
    0.06
    authorized
    0.06
     randomized
    0.06
    _SOURCE
    0.06
     Authorization
    0.06
     lastName
    0.06
     Teh
    0.06
    Act Density 0.005%

    No Known Activations