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

    Neuronpedia

    INDEX
    Explanations

    Average

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    翈
    -0.08
     camouflage
    -0.08
    społeczn
    -0.07
    _checker
    -0.07
     bisexual
    -0.06
     metadata
    -0.06
    $search
    -0.06
     mating
    -0.06
     backup
    -0.06
    自由
    -0.06
    POSITIVE LOGITS
    łoży
    0.08
    ::__
    0.07
    伢
    0.07
    ')}>↵
    0.07
    pong
    0.07
    سى
    0.07
    艅
    0.07
     newY
    0.07
    我心里
    0.07
    磙
    0.07
    Act Density 0.043%

    No Known Activations