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

    Neuronpedia

    INDEX
    Explanations

    convolutional neural networks

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     spiders
    -0.07
     initData
    -0.07
    .writeHead
    -0.07
     PSU
    -0.07
     nuances
    -0.06
     mention
    -0.06
     philosophy
    -0.06
     Sponsor
    -0.06
    服务
    -0.06
     //~
    -0.06
    POSITIVE LOGITS
    вор
    0.07
    bur
    0.06
    custom
    0.06
     Marco
    0.06
     уклад
    0.06
     собствен
    0.06
    legt
    0.06
    month
    0.06
     Ethan
    0.06
    <img
    0.06
    Act Density 0.001%

    No Known Activations