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

    Neuronpedia

    INDEX
    Explanations

    monitoring and its status

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Y
    0.49
     Lupus
    0.47
     Taylor
    0.46
     Ken
    0.46
     Quantum
    0.46
     Kendra
    0.45
     Car
    0.45
     Out
    0.45
     Jenkins
    0.45
     Holland
    0.44
    POSITIVE LOGITS
    ον
    0.51
     அதி
    0.50
    état
    0.47
    UTCDate
    0.46
    އ
    0.46
    ateurs
    0.46
    body
    0.46
     אס
    0.46
     eateries
    0.45
     bữa
    0.45
    Act Density 0.001%

    No Known Activations