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

    Neuronpedia

    INDEX
    Explanations

    act as

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
      
    0.51
    n
    0.50
     BEST
    0.45
     laten
    0.44
    e
    0.44
     most
    0.42
     gavel
    0.42
     bast
    0.42
     \{
    0.42
    s
    0.41
    POSITIVE LOGITS
    ্বরের
    0.48
    நடிக
    0.47
     अवसरों
    0.47
    itarian
    0.45
    újo
    0.44
    იდან
    0.44
    行业的
    0.43
    ولندا
    0.43
    ⏹
    0.43
    🌚
    0.43
    Act Density 0.002%

    No Known Activations