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

    Neuronpedia

    INDEX
    Explanations

    to as

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     soft
    -0.07
     commitments
    -0.07
     training
    -0.07
    vars
    -0.06
     phê
    -0.06
    508
    -0.06
    645
    -0.06
     annotations
    -0.06
     boundaries
    -0.06
     commitment
    -0.06
    POSITIVE LOGITS
    nickname
    0.06
    центра
    0.06
     sewer
    0.06
     вак
    0.06
    (en
    0.06
    』（
    0.06
    quote
    0.06
    yect
    0.06
    (""));↵
    0.06
     setOpen
    0.06
    Act Density 0.029%

    No Known Activations