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

    Neuronpedia

    INDEX
    Explanations

    Board games

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    /sc
    -0.08
     phản
    -0.07
    触
    -0.07
    初中
    -0.07
    _content
    -0.07
     Carp
    -0.07
    _access
    -0.07
    吹
    -0.07
    Matcher
    -0.07
    smith
    -0.06
    POSITIVE LOGITS
    僦
    0.06
     marrow
    0.06
    התחיל
    0.06
    퇀
    0.06
     Phillies
    0.06
    겻
    0.06
    -frequency
    0.06
    夺取
    0.06
     loans
    0.06
    鄗
    0.06
    Act Density 0.013%

    No Known Activations