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

    Neuronpedia

    INDEX
    Explanations

    *

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     serving
    -0.07
    정을
    -0.07
     Shepard
    -0.07
     arg
    -0.07
     nob
    -0.07
     restaurants
    -0.07
    Load
    -0.07
     miejs
    -0.07
     Stanley
    -0.07
    ,email
    -0.06
    POSITIVE LOGITS
     تص
    0.06
    ख
    0.06
     Renderer
    0.06
    SOR
    0.06
    (clazz
    0.06
    вищ
    0.06
    _DISPATCH
    0.06
     شب
    0.06
    Cro
    0.05
     güncel
    0.05
    Act Density 0.012%

    No Known Activations