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

    Neuronpedia

    INDEX
    Explanations

    Venice and anxiety

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    m
    1.16
    in
    1.10
    ie
    1.06
    iv
    0.97
    ssä
    0.97
     in
    0.96
    ifying
    0.89
    ästä
    0.89
    (
    0.87
    ene
    0.86
    POSITIVE LOGITS
    ING
    1.05
     bulunduğu
    0.98
     sayıda
    0.98
    ע
    0.93
     energije
    0.91
    2
    0.91
    EN
    0.91
     वापरा
    0.91
     mnog
    0.90
     lawfully
    0.90
    Act Density 0.006%

    No Known Activations