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

    Neuronpedia

    INDEX
    Explanations

    foreign languages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    er
    1.28
     renegoti
    0.96
    いません
    0.96
    y
    0.95
    oes
    0.94
    hift
    0.91
    teg
    0.91
    oq
    0.89
    いっぱい
    0.89
     deteriorate
    0.88
    POSITIVE LOGITS
     вулкан
    1.00
    Ин
    1.00
     mộ
    0.96
     Fuß
    0.96
    一緒
    0.96
     bū
    0.94
    jenigen
    0.93
    ೇಕ
    0.93
     Einen
    0.93
    ጼ
    0.92
    Act Density 0.000%

    No Known Activations