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

    Neuronpedia

    INDEX
    Explanations

    News snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     รอบ
    -0.06
    avorites
    -0.06
    排名
    -0.06
    ANG
    -0.06
     Mozart
    -0.06
    (ip
    -0.06
     pilgrimage
    -0.06
    _regex
    -0.06
     hell
    -0.06
     saúde
    -0.06
    POSITIVE LOGITS
    Density
    0.07
    响
    0.07
    意
    0.06
     жизни
    0.06
    /json
    0.06
    يش
    0.06
    escaping
    0.06
     suspicious
    0.06
     почти
    0.06
     getObject
    0.06
    Act Density 0.008%

    No Known Activations