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

    Neuronpedia

    INDEX
    Explanations

    agrivoltaics, NAND, stool, IT, миндалины, Hack, human

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    \
    0.46
    *.
    0.46
    .*
    0.44
     ذریع
    0.42
     کی۔
    0.40
     -,
    0.38
     thiab
    0.37
    ங்களையும்
    0.36
     ensued
    0.36
    .]
    0.35
    POSITIVE LOGITS
     does
    0.56
     can
    0.54
     provides
    0.53
     has
    0.52
     is
    0.50
    物は
    0.49
     lacks
    0.48
     tends
    0.48
     have
    0.46
     are
    0.46
    Act Density 0.234%

    No Known Activations