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

    Neuronpedia

    INDEX
    Explanations

    .Fill

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Exchange
    -0.09
    拥挤
    -0.07
     Consultants
    -0.07
    工程师
    -0.07
    ountains
    -0.06
     Mentor
    -0.06
     charges
    -0.06
    砾
    -0.06
    (listener
    -0.06
    manager
    -0.06
    POSITIVE LOGITS
    omatic
    0.07
     pace
    0.07
    落实
    0.07
     '',
↵
    0.07
    ʣ
    0.07
    等形式
    0.07
     justification
    0.07
     racket
    0.07
    ализ
    0.07
    unprocessable
    0.06
    Act Density 0.003%

    No Known Activations