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

    Neuronpedia

    INDEX
    Explanations

    .

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Collection
    1.24
     Collect
    1.17
    Collection
    1.11
     collection
    1.11
    collection
    1.11
     collectibles
    1.04
    Collectible
    0.99
     collectible
    0.99
     collect
    0.99
    Collect
    0.98
    POSITIVE LOGITS
     निघ
    0.74
     empat
    0.71
     pressed
    0.69
     floodplain
    0.69
     flashed
    0.69
     flashing
    0.63
    IfExists
    0.60
     رہنما
    0.60
    后面的
    0.60
     conductivity
    0.60
    Act Density 0.001%

    No Known Activations