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

    Neuronpedia

    INDEX
    Explanations

    people's names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    滬
    0.32
    Whitelist
    0.29
     seroton
    0.28
    ټبال
    0.28
     Notation
    0.28
    ব্ল
    0.28
    异步
    0.27
     بغ
    0.27
    塭
    0.27
    pOt
    0.27
    POSITIVE LOGITS
     Robert
    0.74
     John
    0.71
     Michael
    0.66
     William
    0.65
     Richard
    0.64
     David
    0.62
     Charles
    0.61
     Donald
    0.61
     Joseph
    0.59
    Robert
    0.57
    Act Density 0.040%

    No Known Activations