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

    Neuronpedia

    INDEX
    Explanations

    back on

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    zata
    1.07
     friendly
    1.07
    buz
    1.06
    .\\
    1.06
    atov
    1.05
     Tablet
    1.01
    atz
    1.01
    aty
    1.01
    酵
    0.96
     Cup
    0.96
    POSITIVE LOGITS
     индек
    1.33
    ผล
    1.28
    SHRI
    1.20
     индекс
    1.16
    indice
    1.15
     consequências
    1.15
     détails
    1.15
     ciento
    1.14
     menuItem
    1.14
    Finale
    1.14
    Act Density 0.012%

    No Known Activations