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

    Neuronpedia

    INDEX
    Explanations

    (

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    anonymous
    -0.07
    .block
    -0.07
    human
    -0.07
    аг
    -0.06
    enin
    -0.06
     Garland
    -0.06
    copies
    -0.06
    anding
    -0.06
    isors
    -0.06
     ecology
    -0.06
    POSITIVE LOGITS
     rb
    0.06
     -(
    0.06
    atever
    0.06
     उच
    0.06
    objectManager
    0.06
     perso
    0.06
     дви
    0.06
     depleted
    0.06
    neh
    0.06
    .fullName
    0.06
    Act Density 0.001%

    No Known Activations