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

    Neuronpedia

    INDEX
    Explanations

    thread

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     antivirus
    -0.09
     Hood
    -0.07
     Receiver
    -0.07
     Shiv
    -0.07
     Amph
    -0.07
     Soldiers
    -0.06
    Nd
    -0.06
     XIII
    -0.06
    Sea
    -0.06
     convicted
    -0.06
    POSITIVE LOGITS
    ело
    0.06
    عام
    0.06
    blem
    0.06
    male
    0.06
     memorable
    0.06
    favorite
    0.06
    ade
    0.06
    veled
    0.06
    productId
    0.06
    eyes
    0.06
    Act Density 0.012%

    No Known Activations