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

    Neuronpedia

    INDEX
    Explanations

    legal documents

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     proficiency
    -0.07
    צפייה
    -0.06
    暴雨
    -0.06
    cea
    -0.06
    olicies
    -0.06
     travail
    -0.06
     deutsche
    -0.06
    创业板
    -0.06
     deselect
    -0.06
     de
    -0.06
    POSITIVE LOGITS
    שיע
    0.07
    AMENT
    0.07
    fans
    0.07
    зыва
    0.07
    _expect
    0.06
     aliment
    0.06
    呼ばれ
    0.06
    rant
    0.06
     secretly
    0.06
    ↜
    0.06
    Act Density 0.002%

    No Known Activations