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

    Neuronpedia

    INDEX
    Explanations

    simplicity or smallness

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     always
    0.46
    awsze
    0.46
     alltid
    0.45
     altid
    0.43
    वैसे
    0.42
     sempre
    0.41
     항상
    0.41
    Siempre
    0.40
     areas
    0.40
     அடுத்து
    0.39
    POSITIVE LOGITS
    而已
    0.59
    一个小
    0.54
    短短
    0.52
     humble
    0.52
    だけでも
    0.52
     unassuming
    0.51
     sebuah
    0.50
    だけで
    0.50
    シンプルな
    0.50
     ఒక్క
    0.50
    Act Density 0.094%

    No Known Activations