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

    Neuronpedia

    INDEX
    Explanations

    has

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     cham
    -0.07
     Cz
    -0.07
     Richie
    -0.07
     imap
    -0.07
    임
    -0.07
    separator
    -0.07
     Pu
    -0.06
     overnight
    -0.06
     cupid
    -0.06
    coupon
    -0.06
    POSITIVE LOGITS
     열
    0.06
    打
    0.06
     comparisons
    0.06
     Twelve
    0.06
     العلم
    0.06
     differentiation
    0.06
     рассказ
    0.06
     وابسته
    0.06
     آنجا
    0.06
    (fs
    0.06
    Act Density 0.077%

    No Known Activations