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

    Neuronpedia

    INDEX
    Explanations

    state change or becoming

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     넣어
    0.32
    넣
    0.31
    씀
    0.29
    させ
    0.28
    伸ば
    0.28
    آور
    0.28
     हत्या
    0.27
    使得
    0.27
     올려
    0.27
     நடத்தி
    0.27
    POSITIVE LOGITS
     undergoes
    0.56
     undergo
    0.55
     become
    0.53
     gets
    0.52
     becomes
    0.51
     evolves
    0.50
     fizz
    0.48
    变得
    0.46
     disappears
    0.46
     underwent
    0.45
    Act Density 0.145%

    No Known Activations