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

    Neuronpedia

    INDEX
    Explanations

    numbers and units

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Benzoimidazol
    0.30
    authState
    0.30
     ము
    0.29
    ర్రీ
    0.29
    SupportActionBar
    0.29
    Github
    0.29
     фон
    0.28
     obfusc
    0.28
     Celine
    0.28
     BrowserRouter
    0.28
    POSITIVE LOGITS
    0
    0.46
    2
    0.39
    6
    0.38
    1
    0.38
    3
    0.37
    0.37
    までの
    0.36
    4
    0.36
    8
    0.34
     amperes
    0.33
    Act Density 0.070%

    No Known Activations