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

    Neuronpedia

    INDEX
    Explanations

    feel slightly delayed

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Vintage
    0.43
    Largest
    0.41
    Luxury
    0.40
     Largest
    0.40
    Russian
    0.40
     largest
    0.39
    Chinese
    0.39
    Maui
    0.39
    Worlds
    0.39
    Van
    0.38
    POSITIVE LOGITS
     INTERRUPTION
    0.46
    থমে
    0.43
     direcion
    0.40
     fühlen
    0.39
     الطالب
    0.39
     النش
    0.39
     drin
    0.38
    辫
    0.38
     मुठभे
    0.38
    ﮅ
    0.38
    Act Density 0.002%

    No Known Activations