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

    Neuronpedia

    INDEX
    Explanations

    literature

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     compart
    -0.08
     EXPECT
    -0.07
     fmt
    -0.07
    版权归
    -0.07
     Pey
    -0.07
     proves
    -0.07
     expect
    -0.07
    .float
    -0.07
    ToRemove
    -0.07
     TEntity
    -0.07
    POSITIVE LOGITS
    圬
    0.08
     futuristic
    0.07
     psychedelic
    0.07
    глав
    0.07
    獗
    0.07
    ONEY
    0.07
    香菇
    0.07
     arous
    0.07
    okie
    0.07
     ugly
    0.07
    Act Density 0.001%

    No Known Activations