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

    Neuronpedia

    INDEX
    Explanations

    network

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    وري
    -0.07
     appreciation
    -0.06
     Wal
    -0.06
     precio
    -0.06
    ementia
    -0.06
    ávají
    -0.06
     tracks
    -0.06
    �
    -0.06
    练
    -0.06
    any
    -0.06
    POSITIVE LOGITS
     HelloWorld
    0.07
     Released
    0.06
    .s
    0.06
    到了
    0.06
    ernaut
    0.06
     thriller
    0.06
     namespace
    0.06
    股东
    0.06
    _verbose
    0.06
     Amazing
    0.06
    Act Density 0.010%

    No Known Activations