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

    Neuronpedia

    INDEX
    Explanations

    neural networks

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -online
    -0.07
    munition
    -0.07
    ev
    -0.06
    енная
    -0.06
     Jaune
    -0.06
     suspected
    -0.06
     equality
    -0.06
    енного
    -0.06
    енный
    -0.06
     nécessaire
    -0.06
    POSITIVE LOGITS
    ัศ
    0.07
    .Ship
    0.06
     AUTHORS
    0.06
    (glm
    0.06
    .setPreferredSize
    0.06
     "^
    0.06
    :length
    0.06
    ()%
    0.06
     comments
    0.06
    _hero
    0.06
    Act Density 0.146%

    No Known Activations