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

    Neuronpedia

    INDEX
    Explanations

    months and numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ſe
    1.22
    про
    1.11
    mets
    1.08
    ഹ്ലാദ
    1.07
    kins
    1.07
    ecia
    1.07
    ナー
    1.07
    an
    1.07
    سٹ
    1.06
    quir
    1.05
    POSITIVE LOGITS
     импера
    1.11
    이
    1.10
     с
    1.09
    ிறது
    1.08
    登山
    1.07
    athlon
    1.03
    t
    1.03
     Pellegr
    1.02
    llis
    1.01
    憚
    1.00
    Act Density 0.015%

    No Known Activations