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

    Neuronpedia

    INDEX
    Explanations

    pronunciation guides and non-English words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    d
    0.41
     없다
    0.39
    ∆
    0.39
    nt
    0.38
    less
    0.37
    iw
    0.37
     &
    0.37
    current
    0.37
     current
    0.36
    ঁর
    0.36
    POSITIVE LOGITS
     JavaBean
    0.45
     setCart
    0.44
     "{{
    0.44
    Ｋ
    0.44
    Ｃ
    0.43
     internasional
    0.43
     comen
    0.42
     antitrust
    0.42
    甲基
    0.42
    淆
    0.42
    Act Density 0.013%

    No Known Activations