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

    Neuronpedia

    INDEX
    Explanations

    know technology names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    倖
    1.18
     defraud
    1.17
     infographic
    1.15
     afterthought
    1.14
     isopropyl
    1.13
     smartwatch
    1.11
     investigative
    1.11
     accad
    1.11
     accolade
    1.10
     disposal
    1.10
    POSITIVE LOGITS
    ی
    1.42
    𝙖
    1.41
    िक
    1.41
    𝙚
    1.39
    یث
    1.29
    a
    1.27
    на
    1.26
    𝙤
    1.25
    \\
    1.21
    𝙣
    1.20
    Act Density 0.000%

    No Known Activations