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

    Neuronpedia

    INDEX
    Explanations

    article section headers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ableView
    -0.08
     Defines
    -0.07
     (!((
    -0.07
    hk
    -0.07
     Benchmark
    -0.07
    weak
    -0.07
    وار
    -0.07
    时空
    -0.07
    Zoom
    -0.07
    𐍂
    -0.06
    POSITIVE LOGITS
    حامل
    0.07
    Ì
    0.07
     قامت
    0.07
    CartItem
    0.07
    (action
    0.07
     Can
    0.07
    四
    0.07
    _producto
    0.07
     Ham
    0.07
    Can
    0.07
    Act Density 0.038%

    No Known Activations