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

    Neuronpedia

    INDEX
    Explanations

    smart

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ALOG
    -0.07
     hole
    -0.07
     succeed
    -0.07
    λογ
    -0.07
     bridges
    -0.07
    들도
    -0.07
     recess
    -0.06
     amalg
    -0.06
    ेर
    -0.06
     Všech
    -0.06
    POSITIVE LOGITS
     Smart
    0.07
    awk
    0.07
    StartupScript
    0.06
    605
    0.06
    ้องน
    0.06
     Visual
    0.06
    tparam
    0.06
    (Sql
    0.06
    得
    0.06
    ěn
    0.06
    Act Density 0.004%

    No Known Activations