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

    Neuronpedia

    INDEX
    Explanations

    lists and points

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Admir
    -0.08
     Listen
    -0.08
     transmiss
    -0.08
     listen
    -0.07
     listened
    -0.07
     tug
    -0.07
     controll
    -0.07
     Guil
    -0.07
     QApplication
    -0.07
     மெ
    -0.07
    POSITIVE LOGITS
     excessively
    0.09
     dryness
    0.09
    _ENABLED
    0.08
     exces
    0.08
     excessive
    0.08
     abrupt
    0.07
     demasi
    0.07
    occo
    0.07
     overly
    0.07
     મૃત
    0.07
    Act Density 0.004%

    No Known Activations