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

    Neuronpedia

    INDEX
    Explanations

    within

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    тельные
    -0.08
     frequent
    -0.07
     Mitar
    -0.07
     AppleWebKit
    -0.07
    一听
    -0.07
     Report
    -0.06
    כנה
    -0.06
    (model
    -0.06
     (=
    -0.06
     세상
    -0.06
    POSITIVE LOGITS
    Modules
    0.07
    TRUE
    0.07
     arena
    0.07
    _definition
    0.07
    'b
    0.07
     outputStream
    0.07
    解析
    0.07
    ottie
    0.07
     setters
    0.07
    _logout
    0.07
    Act Density 0.000%

    No Known Activations