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

    Neuronpedia

    INDEX
    Explanations

    online donations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Lemma
    -0.10
     lemma
    -0.09
    invoke
    -0.09
     Lem
    -0.08
    男子
    -0.08
     Invoke
    -0.08
     teoria
    -0.08
    -0.08
     fenomen
    -0.08
     invoke
    -0.08
    POSITIVE LOGITS
     preferred
    0.10
    方式
    0.09
     preference
    0.09
     Preferred
    0.09
     convenience
    0.09
     souhaitent
    0.09
     convenient
    0.09
    愿
    0.08
     preferences
    0.08
     willen
    0.08
    Act Density 0.043%

    No Known Activations