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

    Neuronpedia

    INDEX
    Explanations

    picking

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Kendall
    -0.07
     authorization
    -0.07
    萨
    -0.07
    试点
    -0.07
     Tập
    -0.06
    څ
    -0.06
    さ
    -0.06
    Cert
    -0.06
     Young
    -0.06
    ixture
    -0.06
    POSITIVE LOGITS
     deducted
    0.07
     postpone
    0.07
    Activate
    0.07
    谿
    0.07
     invoke
    0.07
    Invoker
    0.07
     książ
    0.07
     stripped
    0.07
    _Callback
    0.07
    )][
    0.07
    Act Density 0.001%

    No Known Activations