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

    Neuronpedia

    INDEX
    Explanations

    node_modules directory

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ोप
    0.41
    寤
    0.40
    醗
    0.40
    撅
    0.38
     चालू
    0.38
    gerald
    0.37
     एकज
    0.37
    स्कूल
    0.37
     informieren
    0.37
     предстоя
    0.37
    POSITIVE LOGITS
    vendor
    1.11
     vendor
    1.08
    node
    1.00
     node
    0.96
     vendors
    0.82
    Vendor
    0.82
     Vendor
    0.81
     Vendors
    0.71
     Node
    0.68
    Vend
    0.68
    Act Density 0.008%

    No Known Activations