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

    Neuronpedia

    INDEX
    Explanations

    expecting future outcomes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     барои
    0.43
    ltry
    0.41
    ազ
    0.41
     seemingly
    0.40
    缓缓
    0.39
    arily
    0.38
    fections
    0.38
    默默
    0.38
    Cir
    0.38
    afi
    0.38
    POSITIVE LOGITS
    预计
    0.46
     പ്രതീക്ഷ
    0.43
     expect
    0.43
    マシン
    0.43
     there
    0.41
     rencana
    0.40
     machining
    0.39
     break
    0.39
     expected
    0.39
    tema
    0.38
    Act Density 0.001%

    No Known Activations