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

    Neuronpedia

    INDEX
    Explanations

    configuration files and settings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     geometric
    0.45
    mapbox
    0.45
     geo
    0.42
     geometrically
    0.40
     geomet
    0.39
     geometrical
    0.38
    روض
    0.38
    水素
    0.37
    鎬
    0.37
    }^{\#
    0.37
    POSITIVE LOGITS
    XML
    0.55
    Plist
    0.50
     XML
    0.47
    DTDs
    0.46
    Dictionary
    0.45
     NSDictionary
    0.42
    値
    0.41
    InfoPlistPath
    0.40
    dict
    0.40
    Dic
    0.40
    Act Density 0.002%

    No Known Activations