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

    Neuronpedia

    INDEX
    Explanations

    code length specifications

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     meiosis
    0.27
     Yeast
    0.26
    లిన
    0.25
     subdirectory
    0.25
    Dispose
    0.24
     blends
    0.24
    滗
    0.24
    ীবনী
    0.24
     fluorine
    0.24
     unincorporated
    0.24
    POSITIVE LOGITS
    1
    0.32
     των
    0.29
     ۱۰
    0.28
     १०
    0.28
     १००
    0.27
    5
    0.27
     १५
    0.27
    ５
    0.26
    💯
    0.26
    𒐪
    0.26
    Act Density 0.234%

    No Known Activations