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

    Neuronpedia

    INDEX
    Explanations

    browser navigation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     equaling
    0.37
    gor
    0.36
    ৃঙ্খলা
    0.36
     SPORTS
    0.35
    ުމ
    0.35
     установлен
    0.35
    भवती
    0.35
    easeInOut
    0.34
     enctype
    0.34
    シングル
    0.34
    POSITIVE LOGITS
    DELAY
    0.37
    િસ
    0.36
    πάν
    0.36
    ữa
    0.35
    Delay
    0.35
    зва
    0.35
    το
    0.35
    ew
    0.34
     question
    0.34
    Toilet
    0.34
    Act Density 0.002%

    No Known Activations