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

    Neuronpedia

    INDEX
    Explanations

    over

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    �
    -0.07
    lp
    -0.06
    gars
    -0.06
    LBL
    -0.06
    tif
    -0.06
     Constructs
    -0.06
    toolbar
    -0.06
    Người
    -0.06
    Me
    -0.06
    习
    -0.06
    POSITIVE LOGITS
    .styles
    0.06
     bunları
    0.06
     Spain
    0.06
    ing
    0.06
    ])){↵
    0.06
    อบ
    0.06
    Comb
    0.06
    &);↵↵
    0.06
    	Boolean
    0.06
    Colors
    0.06
    Act Density 0.030%

    No Known Activations