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

    Neuronpedia

    INDEX
    Explanations

    that

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    跑
    -0.08
     Ninth
    -0.08
    干警
    -0.07
    审计
    -0.07
     chcia
    -0.07
    壕
    -0.07
     +:+
    -0.07
    有了
    -0.07
    碰撞
    -0.07
    赳
    -0.07
    POSITIVE LOGITS
    ﻁ
    0.07
    커
    0.07
    놐
    0.07
     geomet
    0.07
    dat
    0.07
     adapt
    0.07
     customization
    0.06
    /dat
    0.06
    openhagen
    0.06
    登錄
    0.06
    Act Density 0.001%

    No Known Activations