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

    Neuronpedia

    INDEX
    Explanations

    Python code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    isAdmin
    -0.07
    ۷
    -0.06
    _space
    -0.06
    ยน
    -0.06
     inflate
    -0.06
    inati
    -0.06
     YEAR
    -0.06
    _void
    -0.06
     catalogue
    -0.06
    แต
    -0.06
    POSITIVE LOGITS
     independ
    0.08
    )=(
    0.07
    。(
    0.07
    她的
    0.07
    ्वच
    0.06
     Bund
    0.06
     Remember
    0.06
    _True
    0.06
     greed
    0.06
     Disneyland
    0.06
    Act Density 0.061%

    No Known Activations