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

    Neuronpedia

    INDEX
    Explanations

    duplicated

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     deth
    -0.07
     larger
    -0.07
     Mink
    -0.07
     Lava
    -0.07
     connects
    -0.07
     mink
    -0.07
     demeanor
    -0.07
    ర్ప
    -0.07
     metropolis
    -0.07
     nice
    -0.07
    POSITIVE LOGITS
     unnecessarily
    0.15
     duplication
    0.14
     redundant
    0.13
     inutile
    0.13
     duplic
    0.13
     redund
    0.12
     redundancy
    0.12
     unnecessary
    0.11
     needless
    0.11
     esforços
    0.11
    Act Density 0.016%

    No Known Activations