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

    Neuronpedia

    INDEX
    Explanations

    Not yet done

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     decks
    -0.07
     ла
    -0.07
     Transformers
    -0.07
    -light
    -0.07
    .reflect
    -0.06
    (seconds
    -0.06
    .dt
    -0.06
    olic
    -0.06
     büyük
    -0.06
     sampled
    -0.06
    POSITIVE LOGITS
     adel
    0.06
     Ц
    0.06
     �
    0.06
    orta
    0.06
    .walk
    0.06
     <<↵
    0.06
    _Enc
    0.06
     โรง
    0.06
    .codes
    0.06
     Μ
    0.06
    Act Density 0.069%

    No Known Activations