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

    Neuronpedia

    INDEX
    Explanations

    foundation for

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     सीमा
    0.75
     ocurrido
    0.73
    გილ
    0.71
     ಉಪ
    0.71
    mara
    0.70
    angana
    0.69
    ঞ্
    0.69
    لاھ
    0.69
     considerado
    0.69
    LookAndFeelInfo
    0.68
    POSITIVE LOGITS
     foundation
    1.07
     ভিত্তি
    1.06
     layer
    1.04
     bagi
    0.91
    layer
    0.85
     основу
    0.85
    สู่
    0.82
     Grundlage
    0.82
     foundations
    0.82
     фунда
    0.81
    Act Density 0.151%

    No Known Activations