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

    Neuronpedia

    INDEX
    Explanations

    electron

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    凡事
    -0.07
    臭
    -0.07
    缺乏
    -0.07
    ูก
    -0.07
    tright
    -0.07
     tickets
    -0.07
     startTime
    -0.07
    .LA
    -0.07
    彼此
    -0.07
    .transitions
    -0.07
    POSITIVE LOGITS
    esti
    0.07
    REL
    0.07
    ameleon
    0.07
    ")}↵
    0.07
     amazing
    0.06
     SAVE
    0.06
    ﮨ
    0.06
    EXTERN
    0.06
    RING
    0.06
     unfortunate
    0.06
    Act Density 0.008%

    No Known Activations