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

    Neuronpedia

    INDEX
    Explanations

    i have

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     themselves
    0.48
     असल्यास
    0.48
    なければ
    0.47
    あるいは
    0.45
     examines
    0.42
    하십시오
    0.42
    ใด
    0.42
     ಎಂಬುದ
    0.42
     quelconque
    0.42
     কিংবা
    0.41
    POSITIVE LOGITS
     veldig
    0.77
     väldigt
    0.75
     tengo
    0.69
     myself
    0.68
    我现在
    0.66
     mujhe
    0.66
     ziemlich
    0.65
     очень
    0.64
     мои
    0.64
     velmi
    0.64
    Act Density 0.017%

    No Known Activations