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

    Neuronpedia

    INDEX
    Explanations

    say '*' or '//'

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     الأجنب
    -0.07
    쳑
    -0.07
    _uart
    -0.06
    降临
    -0.06
    舶
    -0.06
     Dart
    -0.06
     �
    -0.06
    _slot
    -0.06
    眵
    -0.06
    래
    -0.06
    POSITIVE LOGITS
     polymer
    0.07
    _MSK
    0.07
     Newest
    0.07
     presses
    0.07
     recon
    0.07
     novo
    0.07
    五个
    0.07
    槊
    0.07
     sniper
    0.07
    poser
    0.06
    Act Density 0.002%

    No Known Activations