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

    Neuronpedia

    INDEX
    Explanations

    Software updates/modifications

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    isbury
    -0.07
     Directory
    -0.07
    مسلم
    -0.07
     Tracker
    -0.07
    declaration
    -0.07
     requer
    -0.07
     номер
    -0.07
     מספיק
    -0.07
     difíc
    -0.07
     hectic
    -0.07
    POSITIVE LOGITS
     warn
    0.08
     sold
    0.07
    .DependencyInjection
    0.07
    (Icons
    0.07
    Sold
    0.07
    _death
    0.06
    _Delete
    0.06
    为中心
    0.06
    オー
    0.06
    Thirty
    0.06
    Act Density 0.133%

    No Known Activations