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

    Neuronpedia

    INDEX
    Explanations

    Emotions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     pues
    -0.07
     kir
    -0.07
     assoc
    -0.06
    UnitTest
    -0.06
     DIR
    -0.06
    Responsive
    -0.06
    .QueryString
    -0.06
     belir
    -0.06
    _REQ
    -0.06
     dados
    -0.06
    POSITIVE LOGITS
    ="%
    0.07
     ​​
    0.07
    娱乐
    0.07
    تف
    0.06
    Getting
    0.06
    .pattern
    0.06
    Utils
    0.06
     Estados
    0.06
    OOD
    0.06
     část
    0.06
    Act Density 0.008%

    No Known Activations