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

    Neuronpedia

    INDEX
    Explanations

    one

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     sexuality
    -0.07
     wraps
    -0.07
    há
    -0.06
    -font
    -0.06
    ”。↵↵
    -0.06
             ↵
    -0.06
     Stage
    -0.06
    itä
    -0.06
    ัญญ
    -0.06
    	fill
    -0.06
    POSITIVE LOGITS
    (Device
    0.06
    ensive
    0.06
     videa
    0.06
    àn
    0.06
    597
    0.06
     Buckingham
    0.06
     سایر
    0.06
    ?q
    0.06
    ッカー
    0.06
    ,msg
    0.06
    Act Density 0.000%

    No Known Activations