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

    Neuronpedia

    INDEX
    Explanations

    lines or length

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Paren
    -0.06
    Center
    -0.06
    258
    -0.06
     REPLACE
    -0.06
     tématu
    -0.06
     Kl
    -0.06
    286
    -0.06
    协
    -0.06
     Six
    -0.06
    015
    -0.05
    POSITIVE LOGITS
    已经
    0.07
    ~~~~
    0.07
    挂
    0.07
    ="{{$
    0.07
    مر
    0.06
    صال
    0.06
     commodity
    0.06
    ],$
    0.06
     žádný
    0.06
     unser
    0.06
    Act Density 0.222%

    No Known Activations