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

    Neuronpedia

    INDEX
    Explanations

    building and creating applications

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     než
    0.45
    事人
    0.44
     nessun
    0.44
    懈
    0.44
    FXML
    0.43
     délais
    0.43
     सौ
    0.41
     nerfs
    0.41
     terza
    0.41
     fielding
    0.41
    POSITIVE LOGITS
    t
    0.62
    д
    0.62
    да
    0.60
     Functions
    0.53
    a
    0.47
    函数
    0.47
    tries
    0.46
    give
    0.45
     Gul
    0.45
     Corn
    0.45
    Act Density 0.004%

    No Known Activations