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

    Neuronpedia

    INDEX
    Explanations

    Medical patient statistics

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _plus
    -0.07
     Scientist
    -0.07
     нер
    -0.07
    .RadioButton
    -0.06
    SignIn
    -0.06
    Damn
    -0.06
     subsidies
    -0.06
     Halloween
    -0.06
    Hel
    -0.06
     Finish
    -0.06
    POSITIVE LOGITS
    <pcl
    0.07
     prostituerte
    0.07
    álně
    0.06
    +↵
    0.06
     فقد
    0.06
    받
    0.06
    porn
    0.06
    něné
    0.06
     inoc
    0.06
    casecmp
    0.06
    Act Density 0.024%

    No Known Activations