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

    Neuronpedia

    INDEX
    Explanations

    final answers or outputs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     early
    0.50
     शुरुआती
    0.46
    开头
    0.46
    Early
    0.46
    Initial
    0.46
     initial
    0.45
     Initial
    0.44
     Early
    0.44
     frühen
    0.44
    early
    0.42
    POSITIVE LOGITS
     final
    1.55
    最後の
    1.48
     अंतिम
    1.45
     마지막
    1.45
    final
    1.38
     FINAL
    1.37
    最后的
    1.34
    最終
    1.33
     Final
    1.31
     आखिरी
    1.30
    Act Density 0.118%

    No Known Activations