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

    Neuronpedia

    INDEX
    Explanations

    national key university laboratory center

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     whiche
    0.68
    となっている
    0.62
    かと思います
    0.62
     Anand
    0.61
    ン
    0.61
     paediatric
    0.60
     wnios
    0.60
     restocking
    0.59
     দিয়াছেন
    0.59
     Muchas
    0.59
    POSITIVE LOGITS
    U
    0.69
    uco
    0.59
    জেলা
    0.59
    、
    0.58
    arbeit
    0.54
    y
    0.54
    VITY
    0.54
    yzed
    0.53
    para
    0.52
    S
    0.52
    Act Density 0.000%

    No Known Activations