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

    Neuronpedia

    INDEX
    Explanations

    requests and content creation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (Common
    -0.07
     cares
    -0.07
    מעלה
    -0.07
     כללי
    -0.07
    iness
    -0.07
    )],↵
    -0.07
     tid
    -0.06
    _CONN
    -0.06
    .dirty
    -0.06
    ---------↵
    -0.06
    POSITIVE LOGITS
     BUG
    0.07
    策划
    0.07
    iropr
    0.07
     doi
    0.06
    ᕑ
    0.06
     Applicant
    0.06
    رص
    0.06
     Wal
    0.06
     appellant
    0.06
    .How
    0.06
    Act Density 0.003%

    No Known Activations