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

    Neuronpedia

    INDEX
    Explanations

    state becomes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     دارند
    0.79
    密集
    0.78
     दस्तक
    0.74
    adă
    0.74
    諱
    0.73
     داره
    0.73
     घेऊ
    0.73
     fah
    0.73
     Están
    0.71
    ்சைடு
    0.70
    POSITIVE LOGITS
     become
    2.63
     becomes
    2.53
    becomes
    2.22
     became
    2.20
    become
    2.12
     becoming
    2.10
     Become
    2.10
    became
    1.89
    Become
    1.83
     devient
    1.74
    Act Density 0.372%

    No Known Activations