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

    Neuronpedia

    INDEX
    Explanations

    mutable references

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    メ
    0.46
    으
    0.44
    을
    0.43
    CameraOpened
    0.43
     janela
    0.42
    0.42
     imitate
    0.40
    在这里
    0.39
     Somehow
    0.39
    ciende
    0.39
    POSITIVE LOGITS
     S
    0.54
     Dispatch
    0.49
     lương
    0.49
    ans
    0.48
     Mortgage
    0.48
     Mus
    0.47
     sworn
    0.47
     Vi
    0.43
     decreto
    0.43
     luật
    0.42
    Act Density 0.001%

    No Known Activations