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

    Neuronpedia

    INDEX
    Explanations

    internal conflict

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     fonts
    -0.08
     df
    -0.08
     invoice
    -0.08
    _df
    -0.07
     Callable
    -0.07
     unig
    -0.07
     하
    -0.07
     jamb
    -0.07
    (df
    -0.07
     Styling
    -0.07
    POSITIVE LOGITS
     compassion
    0.10
     vengeance
    0.10
     বিশ্বাস
    0.09
    ，希望
    0.09
     compassionate
    0.09
     החלט
    0.09
     scop
    0.09
     tragedies
    0.09
     Сейчас
    0.09
     نمی
    0.09
    Act Density 0.087%

    No Known Activations