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

    Neuronpedia

    INDEX
    Explanations

    mere or simply

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    并不
    0.41
    យ៉ាង
    0.37
    并没有
    0.35
     Unless
    0.34
    並不
    0.34
    剡
    0.34
     DCP
    0.33
                                   
    0.32
     unless
    0.32
    至少
    0.32
    POSITIVE LOGITS
     단순히
    0.60
     merely
    0.45
     passively
    0.37
     단순
    0.37
    简单的
    0.35
     mere
    0.34
    Mere
    0.31
    只是
    0.30
     estética
    0.30
     vaan
    0.30
    Act Density 0.196%

    No Known Activations