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

    Neuronpedia

    INDEX
    Explanations

    programming code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Raw
    -0.07
    iltr
    -0.07
    illian
    -0.06
    ()});↵
    -0.06
    �
    -0.06
    <select
    -0.06
     Aur
    -0.06
    icky
    -0.06
    博
    -0.06
    rafted
    -0.06
    POSITIVE LOGITS
    卫生
    0.06
    (title
    0.06
     patri
    0.06
    	this
    0.06
    usk
    0.06
     gain
    0.06
     prophets
    0.06
    .ceil
    0.06
     結
    0.06
     jub
    0.06
    Act Density 0.034%

    No Known Activations