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

    Neuronpedia

    INDEX
    Explanations

    final or last

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    धाना
    0.81
    orphous
    0.80
     सिल्वर
    0.68
    早速
    0.66
     holomorphic
    0.66
    ésus
    0.65
    広が
    0.65
    ាហ
    0.65
     अलै
    0.64
    queros
    0.63
    POSITIVE LOGITS
     final
    4.19
    final
    3.67
     last
    3.58
    最后的
    3.52
     마지막
    3.48
    最后
    3.47
     Final
    3.47
    最後の
    3.47
    最後
    3.42
    Final
    3.37
    Act Density 0.185%

    No Known Activations