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

    Neuronpedia

    INDEX
    Explanations

    Purpose

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    大熊猫
    -0.07
    ={↵
    -0.07
    管家
    -0.07
    .tokenize
    -0.07
    徂
    -0.07
     하나님의
    -0.07
     ${↵
    -0.07
     overly
    -0.07
    ガイ
    -0.07
    _places
    -0.07
    POSITIVE LOGITS
    Silver
    0.07
     manufacturer
    0.07
    尚未
    0.07
    年后
    0.07
    专业知识
    0.07
     Escort
    0.07
    _To
    0.07
     peak
    0.07
    Should
    0.06
    SM
    0.06
    Act Density 0.001%

    No Known Activations