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

    Neuronpedia

    INDEX
    Explanations

    independence

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    즘
    -0.07
     dvěma
    -0.06
     dating
    -0.06
     community
    -0.06
     neighbors
    -0.06
     advisory
    -0.06
    nicas
    -0.06
    .fore
    -0.06
    ньої
    -0.06
    oor
    -0.06
    POSITIVE LOGITS
    。此
    0.07
    �
    0.06
     AN
    0.06
     Ups
    0.06
    istes
    0.06
    DetailView
    0.06
     impuls
    0.06
    ANE
    0.06
    スレ
    0.06
    CLU
    0.06
    Act Density 0.008%

    No Known Activations