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

    Neuronpedia

    INDEX
    Explanations

    predicting outcomes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    chatroom
    0.47
     matemáticas
    0.47
    召
    0.47
     poached
    0.46
     профессии
    0.46
    curves
    0.44
    ULU
    0.44
    mines
    0.44
     ophthalm
    0.44
     próprios
    0.43
    POSITIVE LOGITS
     डिलिवरी
    0.51
     Enlightenment
    0.47
     Game
    0.46
     Sea
    0.46
     सफल
    0.45
     Northern
    0.45
     Black
    0.45
    ឡិច
    0.45
     Alle
    0.44
     Snow
    0.43
    Act Density 0.000%

    No Known Activations