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

    Neuronpedia

    INDEX
    Explanations

    }

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Winston
    -0.07
     Exam
    -0.07
     ARR
    -0.07
    Article
    -0.07
     Melee
    -0.06
     schl
    -0.06
     UDP
    -0.06
     qr
    -0.06
    格尔
    -0.06
    حاضر
    -0.06
    POSITIVE LOGITS
    罘
    0.07
    );\
    0.07
     pathMatch
    0.07
     Kod
    0.07
    ?\
    0.07
    Amazing
    0.07
    (face
    0.06
    !");
↵
    0.06
    escaped
    0.06
    _world
    0.06
    Act Density 0.012%

    No Known Activations