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

    Neuronpedia

    INDEX
    Explanations

    titles and proper nouns

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     referrerpolicy
    -0.60
    awtextra
    -0.59
    exels
    -0.58
    клопе
    -0.58
    ={`/
    -0.57
    /**
    -0.55
     noqa
    -0.52
     offside
    -0.52
     来自
    -0.49
    toprule
    -0.49
    POSITIVE LOGITS
     propOrder
    0.69
    ConstraintMaker
    0.59
     hust
    0.48
     EconPapers
    0.48
     utafitiHapana
    0.47
    嘧
    0.46
     disponibilités
    0.46
     Cru
    0.46
     Har
    0.46
     الإسلامية
    0.45
    Act Density 0.000%

    No Known Activations