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

    Neuronpedia

    INDEX
    Explanations

    be

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     effic
    -0.07
     कप
    -0.06
     پاد
    -0.06
    药
    -0.06
     duplex
    -0.06
     Chick
    -0.06
    /chat
    -0.06
     blades
    -0.06
     Barack
    -0.06
     останні
    -0.06
    POSITIVE LOGITS
     falls
    0.07
    hton
    0.07
    ψης
    0.06
    cope
    0.06
    og
    0.06
    ī
    0.06
    lama
    0.06
    (os
    0.06
    .loc
    0.06
    ls
    0.06
    Act Density 0.550%

    No Known Activations