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

    Neuronpedia

    INDEX
    Explanations

    tuning

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     정
    -0.06
    ろ
    -0.06
    Det
    -0.06
    market
    -0.06
     txt
    -0.06
    最初
    -0.06
     Md
    -0.06
    DEC
    -0.06
     kept
    -0.06
    axy
    -0.06
    POSITIVE LOGITS
     County
    0.06
    ']/
    0.06
    .mutable
    0.06
    ystate
    0.06
     debacle
    0.06
     elusive
    0.06
     Walk
    0.06
     Toby
    0.06
     başkan
    0.06
     νέ
    0.06
    Act Density 0.005%

    No Known Activations