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

    Neuronpedia

    INDEX
    Explanations

    summary judgment

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     OTP
    -0.08
     keypad
    -0.08
    craft
    -0.07
     Creating
    -0.07
     ensures
    -0.07
     Polyn
    -0.07
     õ
    -0.07
     lú
    -0.07
     produces
    -0.07
    ]}
    -0.07
    POSITIVE LOGITS
     prejudice
    0.09
     défense
    0.09
     Judgment
    0.09
     sarcas
    0.08
     defendant
    0.08
     rejecting
    0.08
     Baron
    0.08
     denying
    0.08
     judgment
    0.08
     retaliation
    0.08
    Act Density 0.014%

    No Known Activations