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

    Neuronpedia

    INDEX
    Explanations

    names of famous people

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    สัญญา
    0.38
    熵
    0.38
     범
    0.37
    បញ្ចូល
    0.36
     disagree
    0.35
    νει
    0.35
     DataTable
    0.34
    mittedly
    0.34
     ລ
    0.34
     அல்ல
    0.34
    POSITIVE LOGITS
    榊
    0.43
     hodnot
    0.40
    óch
    0.40
    coordinate
    0.38
    ockets
    0.38
    ắ
    0.37
    താണ്
    0.37
     ماين
    0.37
     manten
    0.36
    翛
    0.36
    Act Density 0.001%

    No Known Activations