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

    Neuronpedia

    INDEX
    Explanations

    RGB channels (C)

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     tokopedia
    0.42
     Bats
    0.40
    ছোট
    0.39
     Cats
    0.37
    kwik
    0.37
    COURSE
    0.37
     Pets
    0.37
     ENTRY
    0.36
     выхода
    0.36
     চেন
    0.36
    POSITIVE LOGITS
     affects
    0.39
     получил
    0.39
     illustrates
    0.39
    received
    0.39
     stimulates
    0.38
     distracting
    0.37
     recibieron
    0.37
     received
    0.36
    Received
    0.36
     recieved
    0.36
    Act Density 0.000%

    No Known Activations