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

    Neuronpedia

    INDEX
    Explanations

    closest

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     wrote
    -0.07
    II
    -0.07
     You
    -0.07
    gems
    -0.07
     Into
    -0.07
    Т
    -0.07
     Said
    -0.07
    ";
    -0.07
    .base
    -0.06
    ाध
    -0.06
    POSITIVE LOGITS
     enfants
    0.07
     dieses
    0.06
     rustic
    0.06
     thuê
    0.06
     irgend
    0.06
    quare
    0.06
    _fa
    0.06
    ่ละ
    0.06
    IntegerField
    0.06
     المللی
    0.06
    Act Density 0.002%

    No Known Activations