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

    Neuronpedia

    INDEX
    Explanations

    without overwriting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Tsh
    0.45
     nieruchomości
    0.45
    🖉
    0.43
     noss
    0.42
     Jenna
    0.42
     অন্য
    0.41
    ιχ
    0.41
     unwarranted
    0.40
    лянчук
    0.40
    CNR
    0.40
    POSITIVE LOGITS
    0
    0.52
    0.47
     Lobby
    0.47
    <0x0D>
    0.44
     comidas
    0.42
    0.42
    4
    0.41
    御
    0.41
    afood
    0.40
     එක
    0.40
    Act Density 0.004%

    No Known Activations