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

    Neuronpedia

    INDEX
    Explanations

    cancellations and refunds

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     stomach
    -0.07
    _equal
    -0.07
     grassroots
    -0.07
     Lung
    -0.07
    	add
    -0.07
    Law
    -0.07
     Banks
    -0.07
     ημέ
    -0.06
     Fathers
    -0.06
    敵
    -0.06
    POSITIVE LOGITS
    一区
    0.07
     consolidation
    0.06
    控
    0.06
    tar
    0.06
    čer
    0.06
    _queryset
    0.06
     fp
    0.06
    $error
    0.05
     premises
    0.05
    çesi
    0.05
    Act Density 0.009%

    No Known Activations