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

    Neuronpedia

    INDEX
    Explanations

    MATLAB programming

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    =settings
    -0.07
     gew
    -0.07
    _GAME
    -0.07
    来这里
    -0.07
    (Location
    -0.06
    语法
    -0.06
     nach
    -0.06
    whose
    -0.06
    篇章
    -0.06
     сф
    -0.06
    POSITIVE LOGITS
     denim
    0.07
     חברת
    0.07
    ﾀ
    0.07
    /styles
    0.07
     Lockheed
    0.07
     linen
    0.06
     navy
    0.06
     Labs
    0.06
    _CENTER
    0.06
     secretly
    0.06
    Act Density 0.120%

    No Known Activations