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

    Neuronpedia

    INDEX
    Explanations

    .

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    的情
    -0.08
     착
    -0.07
     interference
    -0.07
    하였다
    -0.07
     demonic
    -0.07
    离开
    -0.07
     desta
    -0.06
    Snap
    -0.06
     Wal
    -0.06
     Elis
    -0.06
    POSITIVE LOGITS
    MOVE
    0.06
    por
    0.06
    .book
    0.06
    PEAR
    0.06
     allocations
    0.06
    .kernel
    0.06
    /stats
    0.05
    ]]↵
    0.05
    .Pattern
    0.05
     celebrity
    0.05
    Act Density 0.001%

    No Known Activations