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

    Neuronpedia

    INDEX
    Explanations

    Government and institutions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     msgs
    -0.06
     Quar
    -0.06
     gc
    -0.06
     -------------
    -0.06
    tre
    -0.06
     merged
    -0.06
    نده
    -0.06
     meats
    -0.06
    anglicky
    -0.06
     resize
    -0.06
    POSITIVE LOGITS
     joint
    0.07
     navigating
    0.07
    kami
    0.06
     Amer
    0.06
    _FALSE
    0.06
    <TEntity
    0.06
     Teen
    0.06
    лять
    0.06
     Grad
    0.06
    لسل
    0.06
    Act Density 0.071%

    No Known Activations