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

    Neuronpedia

    INDEX
    Explanations

    code or programming

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     rested
    -0.30
     Optim
    -0.29
    /fast
    -0.28
     rewrite
    -0.27
    Rew
    -0.25
    hti
    -0.25
     Bench
    -0.25
    沿
    -0.25
     accepted
    -0.24
    ìħĭ
    -0.24
    POSITIVE LOGITS
    maf
    0.27
    .byId
    0.27
    ê°Ŀ
    0.25
    èĢ§
    0.25
     raids
    0.25
     [#
    0.24
     Federation
    0.24
     federation
    0.23
    æĢ»å±Ģ
    0.23
    ldb
    0.23
    Act Density 0.007%

    No Known Activations