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

    Neuronpedia

    INDEX
    Explanations

    Time passing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     criticize
    -0.07
    -month
    -0.07
    documento
    -0.06
     months
    -0.06
     Year
    -0.06
     retirement
    -0.06
    言って
    -0.06
     Jas
    -0.06
     Income
    -0.06
     vibe
    -0.06
    POSITIVE LOGITS
     tomato
    0.06
    /"↵
    0.06
     Rabbit
    0.06
    ":[
    0.06
    ITY
    0.06
    �
    0.06
    她的
    0.06
    三三
    0.06
    _folders
    0.06
     sided
    0.06
    Act Density 0.053%

    No Known Activations