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

    Neuronpedia

    INDEX
    Explanations

    year/time

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     often
    -0.06
     モ
    -0.06
    小时
    -0.06
    =val
    -0.06
    スコ
    -0.05
    详
    -0.05
     proofs
    -0.05
     MLB
    -0.05
    -week
    -0.05
    plants
    -0.05
    POSITIVE LOGITS
     FONT
    0.07
     Surround
    0.07
     Annual
    0.07
    발
    0.07
    ()}>↵
    0.07
     NSF
    0.07
     }}">↵
    0.06
    _second
    0.06
    .requests
    0.06
     Colors
    0.06
    Act Density 0.148%

    No Known Activations