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

    Neuronpedia

    INDEX
    Explanations

    names of people

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    odnev
    0.22
     कहती
    0.22
     Amended
    0.22
     tačiau
    0.21
    ysteine
    0.21
     its
    0.21
    يارات
    0.20
     illetve
    0.20
     নিজেদের
    0.20
     svojih
    0.19
    POSITIVE LOGITS
     himself
    0.60
    ගේ
    0.34
     نفسه
    0.33
     Himself
    0.32
     hims
    0.30
    和他
    0.30
    ův
    0.28
     Jr
    0.28
     करतो
    0.28
     мог
    0.27
    Act Density 0.029%

    No Known Activations