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

    Neuronpedia

    INDEX
    Explanations

    getattr

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .but
    -0.08
    两个人
    -0.07
     alongside
    -0.07
    <Base
    -0.07
     Immediate
    -0.07
    一秒
    -0.07
    亵
    -0.07
    暾
    -0.07
     INTERVAL
    -0.07
    anel
    -0.07
    POSITIVE LOGITS
    мы
    0.08
    ty
    0.07
    态
    0.07
    界
    0.07
     Phát
    0.07
    ении
    0.07
    bb
    0.07
    kę
    0.07
    acts
    0.07
    刊物
    0.07
    Act Density 0.001%

    No Known Activations