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

    Neuronpedia

    INDEX
    Explanations

    disclaimers

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    下來
    -0.09
    Ed
    -0.07
     them
    -0.07
     paved
    -0.07
    Latitude
    -0.07
    LOS
    -0.07
    �
    -0.07
     Dahl
    -0.07
     مما
    -0.07
    _interp
    -0.07
    POSITIVE LOGITS
     [#
    0.07
     FA
    0.07
     (£
    0.07
     raj
    0.07
    
    0.07
     tweeted
    0.06
     center
    0.06
    澍
    0.06
    ʰ
    0.06
    𝚆
    0.06
    Act Density 0.027%

    No Known Activations