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

    Neuronpedia

    INDEX
    Explanations

    career

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     RELEASE
    -0.07
     Firstly
    -0.07
     menos
    -0.06
    958
    -0.06
    Shopping
    -0.06
    .un
    -0.06
    _EX
    -0.06
    .dt
    -0.06
     srpna
    -0.06
     نمونه
    -0.06
    POSITIVE LOGITS
    [src
    0.07
     freak
    0.06
    categoryId
    0.06
    胆
    0.06
    -opt
    0.06
    -id
    0.06
    》，
    0.06
    -threatening
    0.06
     career
    0.06
    -rock
    0.06
    Act Density 0.004%

    No Known Activations