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

    Neuronpedia

    INDEX
    Explanations

    financial forecasts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    "name
    -0.06
    mada
    -0.06
    literal
    -0.06
     livest
    -0.06
     MBA
    -0.06
     bladder
    -0.06
     Lena
    -0.06
    bung
    -0.06
     왕
    -0.06
    Bah
    -0.06
    POSITIVE LOGITS
     Instructor
    0.07
     turist
    0.06
     механіз
    0.06
     trai
    0.06
    oub
    0.06
    _masks
    0.06
     resta
    0.06
     designs
    0.06
     나라
    0.06
    -&
    0.06
    Act Density 0.008%

    No Known Activations