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

    Neuronpedia

    INDEX
    Explanations

    lycer

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    super
    -0.08
     sandbox
    -0.07
     세상
    -0.07
    	Model
    -0.07
    .replace
    -0.07
    给了我
    -0.07
    	sort
    -0.07
     millennium
    -0.07
    igs
    -0.07
     mContext
    -0.07
    POSITIVE LOGITS
    booking
    0.08
     całej
    0.08
    -being
    0.08
    阿森
    0.07
     Quốc
    0.07
     dak
    0.07
    letics
    0.07
    앨
    0.07
    师生
    0.07
     בע
    0.07
    Act Density 0.003%

    No Known Activations