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

    Neuronpedia

    INDEX
    Explanations

    Code/document formatting

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    夫妻
    -0.27
    追éļı
    -0.26
    çĶŁæŃ»
    -0.26
     internacional
    -0.25
    两个人
    -0.25
    ä¸įæķ¢
    -0.25
    两个
    -0.25
    ceph
    -0.25
     internationally
    -0.24
    otal
    -0.24
    POSITIVE LOGITS
     single
    0.49
     Single
    0.48
    (single
    0.47
    single
    0.45
    åįķä¸Ģ
    0.45
    _SINGLE
    0.43
    åįķ
    0.43
    -single
    0.42
    Single
    0.42
    .single
    0.40
    Act Density 0.087%

    No Known Activations