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

    Neuronpedia

    INDEX
    Explanations

    judgment

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     moll
    -0.08
    اسب
    -0.06
    Kit
    -0.06
    ائع
    -0.06
    ī
    -0.06
     onBlur
    -0.06
     aisle
    -0.06
    萨
    -0.06
    oltip
    -0.06
    ω
    -0.06
    POSITIVE LOGITS
    Georgia
    0.08
    .JFrame
    0.07
     Georgia
    0.07
     tremendous
    0.07
     judgment
    0.07
    aniem
    0.07
     pardon
    0.07
     heavy
    0.07
    heavy
    0.07
     자동
    0.06
    Act Density 0.004%

    No Known Activations