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

    Neuronpedia

    INDEX
    Explanations

    Numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    SPAN
    -0.07
    "No
    -0.07
     Mond
    -0.06
     Pharmaceuticals
    -0.06
     qua
    -0.06
     apo
    -0.05
    intestinal
    -0.05
    erty
    -0.05
    Gar
    -0.05
     Homemade
    -0.05
    POSITIVE LOGITS
    움
    0.07
    {
↵
↵
    0.07
     costa
    0.07
    ,");↵
    0.07
     suck
    0.07
    newValue
    0.07
    NIEnv
    0.06
     المملكة
    0.06
    .RadioButton
    0.06
     Lesser
    0.06
    Act Density 0.009%

    No Known Activations