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

    Neuronpedia

    INDEX
    Explanations

    quotation marks

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     aggravated
    -0.08
     برنامج
    -0.07
    active
    -0.07
    谢谢
    -0.07
    寨
    -0.07
     Elastic
    -0.07
    פט
    -0.07
    ác
    -0.07
     注意
    -0.07
    /javascript
    -0.07
    POSITIVE LOGITS
    PECT
    0.07
     المعار
    0.07
    诼
    0.07
    _fil
    0.07
     relevance
    0.06
     vå
    0.06
    toInt
    0.06
    垞
    0.06
     tyr
    0.06
     tenants
    0.06
    Act Density 0.001%

    No Known Activations