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

    Neuronpedia

    INDEX
    Explanations

    CPI, SSA, CDC, index

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Feb
    0.75
     blir
    0.71
    com
    0.69
     ahor
    0.66
     weist
    0.66
     kompak
    0.66
     permiten
    0.65
     owing
    0.65
     Nov
    0.64
     tiene
    0.64
    POSITIVE LOGITS
    leurs
    0.77
    CLUDE
    0.73
    လမ်း
    0.72
    υ
    0.71
    налу
    0.71
    陶瓷
    0.70
    ተው
    0.70
    城県
    0.70
    linkedExternal
    0.70
    ሆኑ
    0.69
    Act Density 0.022%

    No Known Activations