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

    Neuronpedia

    INDEX
    Explanations

    publications

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (del
    -0.07
    (des
    -0.06
    oment
    -0.06
    �
    -0.06
    _indent
    -0.06
    orie
    -0.06
    rus
    -0.06
    bilder
    -0.06
    됨
    -0.06
     student
    -0.06
    POSITIVE LOGITS
     pellets
    0.07
    Seeder
    0.07
     TIMER
    0.07
     ''}↵
    0.07
     perpetrator
    0.07
    ')==
    0.07
    执
    0.07
     кг
    0.07
     wür
    0.07
     Blu
    0.06
    Act Density 0.033%

    No Known Activations