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

    Neuronpedia

    INDEX
    Explanations

    etc. and similar listing continuations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    和一个
    0.47
    និង
    0.43
    న్ని
    0.40
    했고
    0.38
     pierws
    0.37
     World
    0.37
    每一
    0.37
    그리고
    0.37
     和
    0.36
    玩意
    0.36
    POSITIVE LOGITS
     etc
    2.30
     ইত্যাদি
    1.95
     etcétera
    1.93
     тощо
    1.89
    etc
    1.87
     وغیرہ
    1.84
     usw
    1.80
    等等
    1.77
     आदि
    1.73
     Etc
    1.71
    Act Density 0.367%

    No Known Activations