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

    Neuronpedia

    INDEX
    Explanations

    potential or possible

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    λικά
    -0.08
    OfSize
    -0.07
     Young
    -0.07
    DISABLE
    -0.07
    atories
    -0.07
     Nagar
    -0.06
    _class
    -0.06
    _district
    -0.06
     TestUtils
    -0.06
    	expected
    -0.06
    POSITIVE LOGITS
    �
    0.07
     hunts
    0.06
     future
    0.06
     probing
    0.06
    HORT
    0.06
     phụ
    0.06
     bella
    0.06
     comparer
    0.06
     Gew
    0.06
    eneric
    0.06
    Act Density 0.030%

    No Known Activations