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

    Neuronpedia

    INDEX
    Explanations

    Searching and planning

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Aydın
    -0.08
     Çocuk
    -0.07
     afect
    -0.07
    фек
    -0.06
     \|
    -0.06
     مرکز
    -0.06
    diamond
    -0.06
    φό
    -0.06
     toi
    -0.06
     muslim
    -0.06
    POSITIVE LOGITS
    "]
↵
    0.06
            	↵
    0.06
     ()
↵
    0.06
     src
    0.06
    UR
    0.06
    蓝
    0.06
     NavBar
    0.06
    -cookie
    0.06
    شي
    0.06
    /problems
    0.06
    Act Density 0.000%

    No Known Activations