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

    Neuronpedia

    INDEX
    Explanations

    Number 5

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    expandindo
    -0.88
     Baillargeon
    -0.84
     незавершена
    -0.83
    المناصب
    -0.77
    MLLoader
    -0.77
     يتيمه
    -0.76
    DockStyle
    -0.67
    mergeFrom
    -0.65
     bezeichneter
    -0.65
    findpost
    -0.64
    POSITIVE LOGITS
    5
    0.59
     trefoil
    0.46
     five
    0.44
     Chrom
    0.44
     quin
    0.43
     TSP
    0.43
     fifth
    0.42
    scrollY
    0.42
     Apostle
    0.41
     cha
    0.41
    Act Density 0.000%

    No Known Activations