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

    Neuronpedia

    INDEX
    Explanations

    Floating-point numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    092
    -0.07
     desk
    -0.06
    907
    -0.06
    -guard
    -0.06
     vez
    -0.06
    kest
    -0.06
    atown
    -0.06
     veces
    -0.06
     elk
    -0.06
    591
    -0.06
    POSITIVE LOGITS
     wonders
    0.07
     apresent
    0.06
    Project
    0.06
     майбут
    0.06
     уяв
    0.06
    alex
    0.06
    JSONObject
    0.06
    UNDER
    0.06
    unittest
    0.06
    UPDATE
    0.06
    Act Density 0.015%

    No Known Activations