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

    Neuronpedia

    INDEX
    Explanations

    sell

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Dou
    -0.06
     imap
    -0.06
     Sexy
    -0.06
    !',
    -0.06
     dầu
    -0.06
     entender
    -0.06
    	intent
    -0.05
     فت
    -0.05
    .getAs
    -0.05
     ورود
    -0.05
    POSITIVE LOGITS
     replicate
    0.07
     đánh
    0.07
    rish
    0.07
     등을
    0.07
     MST
    0.07
     Bre
    0.06
     Dumbledore
    0.06
    Likes
    0.06
     спеці
    0.06
    _matrices
    0.06
    Act Density 0.162%

    No Known Activations