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

    Neuronpedia

    INDEX
    Explanations

    preparing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    neg
    -0.07
    iven
    -0.07
    .TextView
    -0.07
     Keith
    -0.07
     Joel
    -0.07
     App
    -0.07
    们
    -0.07
     엘
    -0.07
     Chanel
    -0.06
     trailer
    -0.06
    POSITIVE LOGITS
    atische
    0.06
     comunidad
    0.06
     Manafort
    0.06
     виход
    0.05
     storia
    0.05
    urum
    0.05
    つけ
    0.05
    мати
    0.05
     uphol
    0.05
    ować
    0.05
    Act Density 0.047%

    No Known Activations