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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    《
    -0.07
    Retrieve
    -0.07
     personality
    -0.07
     trabalho
    -0.07
    愛情
    -0.07
    rü
    -0.07
     '>
    -0.07
    ř
    -0.07
    _blueprint
    -0.06
    .imread
    -0.06
    POSITIVE LOGITS
    鄭
    0.07
     предост
    0.07
     Nug
    0.07
    Lang
    0.06
    阐明
    0.06
    idges
    0.06
    白沙
    0.06
    (changes
    0.06
    _De
    0.06
     pa
    0.06
    Act Density 0.270%

    No Known Activations