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

    Neuronpedia

    INDEX
    Explanations

    {{

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -buffer
    -0.07
     square
    -0.07
     Gem
    -0.07
     Convenient
    -0.07
     predetermined
    -0.07
    ih
    -0.07
    agento
    -0.07
    .Arg
    -0.06
    ortality
    -0.06
    禁
    -0.06
    POSITIVE LOGITS
    -ม
    0.06
    Verified
    0.06
     evade
    0.06
     Listed
    0.06
     plus
    0.05
    assist
    0.05
     Eylül
    0.05
     mHandler
    0.05
    alia
    0.05
    (join
    0.05
    Act Density 0.002%

    No Known Activations