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

    Neuronpedia

    INDEX
    Explanations

    translate text

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ricorda
    0.42
     remembers
    0.40
     qualche
    0.40
     numberWith
    0.39
    當年
    0.38
     dedicado
    0.38
     belki
    0.38
     recuer
    0.37
     rappelle
    0.37
     lekker
    0.36
    POSITIVE LOGITS
    以下の
    1.09
    下記の
    1.08
     given
    1.07
     निम्नलिखित
    1.05
     seguente
    0.99
     aşağıdaki
    0.95
    以下
    0.94
    निम्नलिखित
    0.94
     berikut
    0.94
    下列
    0.94
    Act Density 0.103%

    No Known Activations