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

    Neuronpedia

    INDEX
    Explanations

    analysis

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ূর্ণ
    -0.08
     WS
    -0.08
    到了
    -0.08
    ******/↵
    -0.08
     Lietuvos
    -0.08
     Российской
    -0.08
    গ্ন
    -0.08
     życie
    -0.07
    ৫০
    -0.07
     白
    -0.07
    POSITIVE LOGITS
    (dec
    0.09
    arella
    0.09
     момента
    0.08
     scans
    0.08
    ecu
    0.07
     untouched
    0.07
     gonna
    0.07
     hehe
    0.07
     briefly
    0.07
     hone
    0.07
    Act Density 0.146%

    No Known Activations