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

    Neuronpedia

    INDEX
    Explanations

    notes and disclaimers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     extremes
    0.33
     paragraph
    0.32
     niezb
    0.32
    lení
    0.31
     පේශ
    0.30
    一是
    0.29
     penyebab
    0.29
     정의역
    0.29
    ość
    0.29
    otipi
    0.29
    POSITIVE LOGITS
    NOTE
    0.46
     NOTE
    0.43
     Note
    0.37
    Note
    0.36
     Nota
    0.31
     Disclaimer
    0.31
     utilizando
    0.30
     übrigens
    0.30
     BTW
    0.29
    请
    0.29
    Act Density 0.437%

    No Known Activations