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

    Neuronpedia

    INDEX
    Explanations

    capacity

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _ve
    -0.08
     bowls
    -0.07
    봄
    -0.07
    #================================================================
    -0.07
     pumped
    -0.07
    tweets
    -0.07
     urges
    -0.07
     ez
    -0.06
    そう
    -0.06
     boo
    -0.06
    POSITIVE LOGITS
     capacity
    0.08
     Capacity
    0.08
    פק
    0.07
     anarchist
    0.07
     contractual
    0.07
     customer
    0.07
    홱
    0.07
    DataAdapter
    0.07
    ㋥
    0.07
     csvfile
    0.07
    Act Density 0.009%

    No Known Activations