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

    Neuronpedia

    INDEX
    Explanations

    _modules

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     assh
    -0.07
     waged
    -0.07
    umble
    -0.07
     fighter
    -0.06
    _skin
    -0.06
    创造出
    -0.06
     proceedings
    -0.06
     ä
    -0.06
     pulp
    -0.06
    /Game
    -0.06
    POSITIVE LOGITS
     Apostle
    0.07
    Sphere
    0.07
     PAR
    0.07
    quiries
    0.07
     colonies
    0.06
     OC
    0.06
    .land
    0.06
     refreshToken
    0.06
    monthly
    0.06
     Waterloo
    0.06
    Act Density 0.000%

    No Known Activations