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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ately
    -0.08
    .obj
    -0.07
    iences
    -0.07
    aron
    -0.07
     alternatively
    -0.07
     ride
    -0.06
     medicine
    -0.06
     Рас
    -0.06
     Assets
    -0.06
    ava
    -0.06
    POSITIVE LOGITS
    "=>"
    0.07
    �
    0.06
     себ
    0.06
     Nä
    0.06
    .Hosting
    0.06
    \DependencyInjection
    0.06
    "=>
    0.06
     Buccaneers
    0.06
    .clientX
    0.06
    rocess
    0.06
    Act Density 0.267%

    No Known Activations