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

    Neuronpedia

    INDEX
    Explanations

    gag

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    农
    -0.07
     Конститу
    -0.07
    ěř
    -0.07
    Sol
    -0.07
     sucht
    -0.06
    남
    -0.06
    식을
    -0.06
    _order
    -0.06
    lected
    -0.06
     landslide
    -0.06
    POSITIVE LOGITS
     gag
    0.12
     gadgets
    0.07
     Restr
    0.06
    ゲ
    0.06
     eager
    0.06
     grappling
    0.06
     gore
    0.06
     jLabel
    0.06
     gambling
    0.06
    query
    0.06
    Act Density 0.001%

    No Known Activations