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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ,*
    -0.07
     هج
    -0.07
    _ev
    -0.07
    (...)
    -0.07
    ूँ
    -0.06
     [],
    -0.06
    iti
    -0.06
    _ident
    -0.06
    -0.06
    _iteration
    -0.06
    POSITIVE LOGITS
     bytecode
    0.08
    -folder
    0.07
    chains
    0.06
     внес
    0.06
     Vij
    0.06
     movement
    0.06
     Boxes
    0.06
     poop
    0.06
     RDD
    0.06
     commonplace
    0.06
    Act Density 0.012%

    No Known Activations