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

    Neuronpedia

    INDEX
    Explanations

    data filtering

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    スト
    -0.07
    ");
↵
↵
    -0.07
     블
    -0.07
    =W
    -0.06
     adap
    -0.06
    ght
    -0.06
     ee
    -0.06
     evet
    -0.06
     επί
    -0.06
     mogelijk
    -0.06
    POSITIVE LOGITS
     follower
    0.07
    fieldName
    0.07
    Indices
    0.07
    елич
    0.07
     flourishing
    0.06
     Haut
    0.06
     eligibility
    0.06
     celery
    0.06
    BIND
    0.06
    EqualTo
    0.06
    Act Density 0.001%

    No Known Activations