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

    Neuronpedia

    INDEX
    Explanations

    after the

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Marines
    0.90
     exuberant
    0.82
     unreal
    0.81
    encies
    0.80
    ビニ
    0.80
     preconceived
    0.80
     purse
    0.79
     kernel
    0.79
    elleen
    0.77
     tag
    0.76
    POSITIVE LOGITS
    Town
    0.76
    Tam
    0.75
    GST
    0.75
    Ton
    0.73
    Tal
    0.72
    Sho
    0.71
    Target
    0.69
    Vale
    0.69
    小于
    0.69
    吿
    0.68
    Act Density 0.001%

    No Known Activations