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

    Neuronpedia

    INDEX
    Explanations

    existence, state, change

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     võivad
    0.32
     اینکه
    0.30
     eğer
    0.29
     اگر
    0.28
    เมื่อ
    0.27
     करताना
    0.26
     berharap
    0.26
    会让
    0.26
     deberá
    0.25
     রাখবে
    0.25
    POSITIVE LOGITS
     became
    0.34
     went
    0.32
     came
    0.31
     wurde
    0.31
     happened
    0.30
     gets
    0.29
     was
    0.28
     become
    0.27
     got
    0.27
     happens
    0.26
    Act Density 0.454%

    No Known Activations