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

    Neuronpedia

    INDEX
    Explanations

    glacial and snow melt

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     theorist
    0.50
     southernmost
    0.47
    녕하세요
    0.46
     insulting
    0.45
    任何
    0.45
     کوډ
    0.45
     günst
    0.45
    ίν
    0.45
    Но
    0.45
    回事
    0.45
    POSITIVE LOGITS
    k
    0.55
    tion
    0.53
    ¹
    0.53
    PX
    0.52
     takeaways
    0.52
    itin
    0.51
    ก
    0.50
    stoff
    0.49
     and
    0.49
    iance
    0.49
    Act Density 0.001%

    No Known Activations