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

    Neuronpedia

    INDEX
    Explanations

    product and sum operations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     nuova
    0.60
     nuove
    0.53
     começa
    0.51
     commence
    0.50
    💳
    0.49
     neues
    0.49
     nueva
    0.49
     nowego
    0.49
     stava
    0.48
     wurde
    0.48
    POSITIVE LOGITS
     mixers
    0.44
    otros
    0.39
     planters
    0.39
    oll
    0.38
     terlibat
    0.38
    attrib
    0.38
    fisher
    0.37
    All
    0.36
    3
    0.36
     भाषाओं
    0.36
    Act Density 0.001%

    No Known Activations