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

    Neuronpedia

    INDEX
    Explanations

    consequences and abstract noun suffixes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     somewhat
    0.38
     некоторые
    0.35
     niektórych
    0.35
    的一些
    0.34
     components
    0.33
    可能会
    0.33
     may
    0.32
     certaines
    0.32
     tertentu
    0.32
    пециа
    0.32
    POSITIVE LOGITS
     ogrom
    0.42
     centaines
    0.40
     enormes
    0.36
     हजारों
    0.36
    Nunca
    0.35
     tué
    0.35
     Сколько
    0.34
     vraie
    0.34
     echte
    0.34
     skyrock
    0.33
    Act Density 0.436%

    No Known Activations