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

    Neuronpedia

    INDEX
    Explanations

    .

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Motor
    -0.07
     Secure
    -0.07
     XR
    -0.06
     mô
    -0.06
    овани
    -0.06
    --){↵
    -0.06
     подраз
    -0.06
    naz
    -0.06
     sizi
    -0.06
     CLEAR
    -0.06
    POSITIVE LOGITS
    ública
    0.07
     Beste
    0.06
     evaluating
    0.06
    ür
    0.06
     cookies
    0.06
     impairment
    0.06
     further
    0.06
    ograms
    0.06
    WithError
    0.06
     alternatively
    0.06
    Act Density 0.149%

    No Known Activations