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

    Neuronpedia

    INDEX
    Explanations

    Removing duplicates from sets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Warp
    -0.10
     Warp
    -0.09
     warp
    -0.09
     planes
    -0.08
     War
    -0.08
    .zz
    -0.07
     pancre
    -0.07
     eignen
    -0.07
     арен
    -0.07
     tiled
    -0.07
    POSITIVE LOGITS
    duplicates
    0.11
    _duplicates
    0.10
     duplicates
    0.10
    mere
    0.09
    membership
    0.09
    memor
    0.09
    Duplicates
    0.09
    unordered
    0.09
    idio
    0.09
    ازد
    0.09
    Act Density 0.012%

    No Known Activations