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

    Neuronpedia

    INDEX
    Explanations

    numerical values and quantities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ŠE
    0.44
    뀔
    0.43
     резко
    0.43
    spiracy
    0.42
    íte
    0.40
    мышлен
    0.40
    вичай
    0.40
    衝撃
    0.40
    ≳
    0.39
    뀜
    0.39
    POSITIVE LOGITS
    5
    0.63
     five
    0.55
    3
    0.52
     ৫
    0.51
    ５
    0.50
    4
    0.48
    2
    0.47
    6
    0.47
     ۵
    0.45
     half
    0.44
    Act Density 0.060%

    No Known Activations