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

    Neuronpedia

    INDEX
    Explanations

    STRACT

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    öff
    -0.08
    яв
    -0.07
     neden
    -0.07
     Trojan
    -0.07
     görün
    -0.07
     Ped
    -0.07
    RadioButton
    -0.06
    McC
    -0.06
    centre
    -0.06
     Aure
    -0.06
    POSITIVE LOGITS
    instrument
    0.08
    pected
    0.07
    非
    0.07
     تخصص
    0.06
    ική
    0.06
    	instance
    0.06
    Father
    0.06
     assembler
    0.06
    <thead
    0.06
    ЕТ
    0.06
    Act Density 0.001%

    No Known Activations