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
    çiler
    -0.07
     _______,
    -0.07
     unauthorized
    -0.06
    系
    -0.06
     citizens
    -0.06
    lights
    -0.06
    々
    -0.06
    "On
    -0.06
     altitude
    -0.06
     IV
    -0.06
    POSITIVE LOGITS
    .
↵
↵
    0.07
    lations
    0.07
     suprem
    0.06
     formal
    0.06
     unc
    0.06
    由
    0.06
    053
    0.06
    _review
    0.06
     корпус
    0.06
    ?;↵↵
    0.06
    Act Density 0.000%

    No Known Activations