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

    Neuronpedia

    INDEX
    Explanations

    living and lived states

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    consolid
    0.34
    tags
    0.31
    verläss
    0.31
    console
    0.29
    емые
    0.29
    acchati
    0.29
    チョコ
    0.29
    Tags
    0.29
    ্রম
    0.28
    巩
    0.28
    POSITIVE LOGITS
     lived
    0.59
     hidup
    0.54
     lives
    0.50
     vivir
    0.48
     прожи
    0.46
     living
    0.46
     happily
    0.46
    lived
    0.44
     жить
    0.44
     生活
    0.43
    Act Density 0.016%

    No Known Activations