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

    Neuronpedia

    INDEX
    Explanations

    numbers and quantities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     bioquímica
    0.26
     등에
    0.25
    법
    0.25
    စ္စည်း
    0.24
    𒂠
    0.24
     objectMapper
    0.24
    摒
    0.24
    лык
    0.23
    姏
    0.23
     एक्सरे
    0.23
    POSITIVE LOGITS
    6
    0.37
    2
    0.34
    1
    0.34
    3
    0.33
    8
    0.32
    ↵
    0.31
    5
    0.31
    7
    0.31
    с
    0.30
    ти
    0.29
    Act Density 0.132%

    No Known Activations