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

    Neuronpedia

    INDEX
    Explanations

    examples and questions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    자를
    0.48
     supérieur
    0.45
     학
    0.45
    전을
    0.43
    宻
    0.42
    臬
    0.42
    લમાં
    0.41
    กฏ
    0.40
     religiosas
    0.40
    entropy
    0.40
    POSITIVE LOGITS
    ńska
    0.39
     food
    0.38
    spawn
    0.38
     एंड
    0.38
     USED
    0.38
     👋
    0.38
     CAN
    0.37
    ierung
    0.37
    food
    0.36
     Cost
    0.36
    Act Density 0.002%

    No Known Activations