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

    Neuronpedia

    INDEX
    Explanations

    involving or conducting thorough

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    abol
    1.39
     inherently
    1.32
    ore
    1.24
     bagno
    1.22
    osz
    1.17
    oare
    1.16
     outright
    1.16
    acquisto
    1.15
    ategori
    1.15
    臘
    1.13
    POSITIVE LOGITS
     tabl
    0.96
     Kirkpatrick
    0.95
     qt
    0.87
     jt
    0.86
    졍
    0.85
     Jahn
    0.84
     Millie
    0.84
     HJ
    0.83
    munk
    0.82
     semaine
    0.81
    Act Density 0.059%

    No Known Activations