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
    dw
    -0.07
    Models
    -0.07
     territory
    -0.07
     running
    -0.06
    DbContext
    -0.06
    _patterns
    -0.06
    Looks
    -0.06
    hores
    -0.06
    $value
    -0.06
    ancybox
    -0.06
    POSITIVE LOGITS
     Mul
    0.06
     Vermont
    0.06
     descricao
    0.06
    )';↵
    0.06
    igte
    0.06
     druhý
    0.06
    관리자
    0.06
     thinkers
    0.06
     창
    0.06
    ="?
    0.06
    Act Density 0.043%

    No Known Activations