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

    Neuronpedia

    INDEX
    Explanations

    selection

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    莫
    -0.08
     parties
    -0.07
     JP
    -0.07
    Push
    -0.07
    ớp
    -0.07
    /products
    -0.06
     คล
    -0.06
    getResponse
    -0.06
     movers
    -0.06
     adapting
    -0.06
    POSITIVE LOGITS
    ）。↵
    0.06
     numel
    0.06
    лерг
    0.06
    aroo
    0.06
    增
    0.06
    _eval
    0.06
    imagin
    0.06
    ？↵
    0.06
    ійно
    0.06
    優
    0.06
    Act Density 0.000%

    No Known Activations