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

    Neuronpedia

    INDEX
    Explanations

    valuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    晚
    -0.07
     링
    -0.07
    ("{\"
    -0.06
     races
    -0.06
    ัง
    -0.06
    _strcmp
    -0.06
    /AIDS
    -0.06
    漂
    -0.06
     majestic
    -0.06
     seaside
    -0.06
    POSITIVE LOGITS
    esz
    0.07
    ürk
    0.07
     đích
    0.06
     untrue
    0.06
     splitter
    0.06
    شماری
    0.06
     markup
    0.06
     Naval
    0.06
     devis
    0.06
     연락
    0.06
    Act Density 0.005%

    No Known Activations